Triple

T25788761
Position Surface form Disambiguated ID Type / Status
Subject Department of the Environment E649491 entity
Predicate hadAgency P159515 FINISHED
Object Building Research Establishment
The Building Research Establishment is a leading UK center for research, testing, and consultancy in building science, construction, and the built environment.
 E1694460 NE FINISHED

How this triple was built (3 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: Building Research Establishment | Statement: [Department of the Environment, hadAgency, Building Research Establishment]
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: Building Research Establishment
Triple: [Department of the Environment, hadAgency, Building Research Establishment]
Generated description
The Building Research Establishment is a leading UK center for research, testing, and consultancy in building science, construction, and the built environment.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hadAgency
Context triple: [Department of the Environment, hadAgency, Building Research Establishment]
  • A. hasAgencyInPlot
    Indicates that an entity actively influences or drives events within the narrative’s plot.
  • B. hadOrganization
    Indicates that an entity was affiliated with, employed by, or otherwise formally associated with a particular organization during some period of time.
  • C. usedByAgency
    Indicates that something (such as a resource, tool, or service) is utilized or employed by an agency.
  • D. hasAgent
    Indicates that an action or event is carried out or initiated by a particular agent.
  • E. agency
    Indicates that an entity acts on behalf of, represents, or exercises power or control for another entity in performing an action or fulfilling a role.
  • F. None of above. chosen

Provenance (7 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_69e7ab33e9308190afe415dc6f9e8876 completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f5fefdad688190920ab174228033c7 completed May 2, 2026, 1:41 p.m.
NED1 Entity disambiguation (via context triple) batch_6a10cc2a56e08190b89e5f3fe4fcd02a completed May 22, 2026, 9:35 p.m.
NEDg Description generation batch_6a10ccbbd8748190af5429ed417fd61f completed May 22, 2026, 9:38 p.m.
NED2 Entity disambiguation (via description) batch_6a10cdbc645881909f0c2da445ee41f6 completed May 22, 2026, 9:42 p.m.
PD Predicate disambiguation batch_69f4a0fed15881909b789251fe5d8d45 completed May 1, 2026, 12:47 p.m.
PDg Predicate description generation batch_69f55e497fa081909bc59a7b92c5df59 completed May 2, 2026, 2:15 a.m.
Created at: April 22, 2026, 5:57 a.m.