Triple

T29048226
Position Surface form Disambiguated ID Type / Status
Subject Place d'Alésia E735192 entity
Predicate hasNearbyMunicipalFacility P5648 FINISHED
Object Mairie annexe of the 14th arrondissement
The Mairie annexe of the 14th arrondissement is a local branch of the Paris town hall providing administrative and civic services to residents of the 14th district.
 E1847252 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: Mairie annexe of the 14th arrondissement | Statement: [Place d'Alésia, hasNearbyMunicipalFacility, Mairie annexe of the 14th arrondissement]
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: Mairie annexe of the 14th arrondissement
Triple: [Place d'Alésia, hasNearbyMunicipalFacility, Mairie annexe of the 14th arrondissement]
Generated description
The Mairie annexe of the 14th arrondissement is a local branch of the Paris town hall providing administrative and civic services to residents of the 14th district.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasNearbyMunicipalFacility
Context triple: [Place d'Alésia, hasNearbyMunicipalFacility, Mairie annexe of the 14th arrondissement]
  • A. hasNearbyFacility chosen
    Indicates that one entity is located close to or in the vicinity of a particular facility.
  • B. isMunicipalityNear
    Indicates that one municipality is located close to another municipality or geographic reference point.
  • C. hasMunicipalitySeatNearby
    Indicates that the municipality’s administrative seat is located in close proximity to the referenced place or entity.
  • D. hasNearbyCommercialFacilities
    Indicates that a place is located close to one or more commercial facilities, such as shops, restaurants, or other businesses.
  • E. hasCivicAmenity
    Indicates that an entity possesses, provides, or is associated with a public facility or service intended for community use.
  • F. None of above.

Provenance (6 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_69f077e64b88819094d37bdbca8191b3 completed April 28, 2026, 9:03 a.m.
NER Named-entity recognition batch_69fddf721c1481909301a0f379368f10 completed May 8, 2026, 1:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a251f738e00819092cb24795dd594d1 completed June 7, 2026, 7:36 a.m.
NEDg Description generation batch_6a252349bdcc8190a167f8376cf6c58f completed June 7, 2026, 7:52 a.m.
NED2 Entity disambiguation (via description) batch_6a2527fa35c481909dcfac5d18038aed completed June 7, 2026, 8:12 a.m.
PD Predicate disambiguation batch_69fddda1ae7c8190b5848ff9a9e39826 completed May 8, 2026, 12:57 p.m.
Created at: April 28, 2026, 10:06 a.m.