Triple

T18036771
Position Surface form Disambiguated ID Type / Status
Subject Montpellier city campus E431526 entity
Predicate partOf P40 FINISHED
Object University of Montpellier campus network
The University of Montpellier campus network is a multi-site higher education system that brings together the university’s various campuses and facilities across Montpellier into a unified academic and research environment.
E1302091 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: University of Montpellier campus network | Statement: [Montpellier city campus, partOf, University of Montpellier campus network]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: University of Montpellier campus network
Context triple: [Montpellier city campus, partOf, University of Montpellier campus network]
  • A. University of Barcelona campus network
    The University of Barcelona campus network is a multi-campus system of university sites across Barcelona that collectively host the institution’s teaching, research, and student services facilities.
  • B. University of Basel campus network
    The University of Basel campus network is the integrated system of university sites and facilities, including the Life Sciences campus, that supports the institution’s academic, research, and administrative activities.
  • C. University of Granada campuses network
    The University of Granada campuses network is the integrated system of all the university’s geographically distributed campuses, including those in mainland Spain and its autonomous cities, coordinated under a single institutional framework.
  • D. University of São Paulo campus network
    The University of São Paulo campus network is the integrated system of USP campuses and facilities across the state of São Paulo, supporting education, research, and extension activities in multiple fields.
  • E. University of Helsinki campus network
    The University of Helsinki campus network is the integrated system of the university’s distinct campuses across Helsinki, each specializing in different academic fields and research areas.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: University of Montpellier campus network
Triple: [Montpellier city campus, partOf, University of Montpellier campus network]
Generated description
The University of Montpellier campus network is a multi-site higher education system that brings together the university’s various campuses and facilities across Montpellier into a unified academic and research environment.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: University of Montpellier campus network
Target entity description: The University of Montpellier campus network is a multi-site higher education system that brings together the university’s various campuses and facilities across Montpellier into a unified academic and research environment.
  • A. University of Barcelona campus network
    The University of Barcelona campus network is a multi-campus system of university sites across Barcelona that collectively host the institution’s teaching, research, and student services facilities.
  • B. University of Basel campus network
    The University of Basel campus network is the integrated system of university sites and facilities, including the Life Sciences campus, that supports the institution’s academic, research, and administrative activities.
  • C. University of Granada campuses network
    The University of Granada campuses network is the integrated system of all the university’s geographically distributed campuses, including those in mainland Spain and its autonomous cities, coordinated under a single institutional framework.
  • D. University of São Paulo campus network
    The University of São Paulo campus network is the integrated system of USP campuses and facilities across the state of São Paulo, supporting education, research, and extension activities in multiple fields.
  • E. University of Helsinki campus network
    The University of Helsinki campus network is the integrated system of the university’s distinct campuses across Helsinki, each specializing in different academic fields and research areas.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8b9050fb48190890155145deb0a66 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4be3a80508190b667c3f6d14f5c84 completed April 19, 2026, 11:36 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0349b345148190b500996adc2c4d6f completed May 12, 2026, 3:39 p.m.
NEDg Description generation batch_6a034a6325b881909f8b21f25c88c561 completed May 12, 2026, 3:42 p.m.
NED2 Entity disambiguation (via description) batch_6a034b35b618819086373115fea686ad completed May 12, 2026, 3:45 p.m.
Created at: April 10, 2026, 10:25 a.m.