Triple

T31780022
Position Surface form Disambiguated ID Type / Status
Subject Chevilly-Larue E811174 entity
Predicate nearTramwayLine P172293 FINISHED
Object Île-de-France tramway Line T7
Île-de-France tramway Line T7 is a suburban tram line in the Paris region that connects the southern outskirts, including areas near Orly Airport, to the wider Île-de-France public transport network.
 E1978544 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: Île-de-France tramway Line T7 | Statement: [Chevilly-Larue, nearTramwayLine, Île-de-France tramway Line T7]
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: Île-de-France tramway Line T7
Triple: [Chevilly-Larue, nearTramwayLine, Île-de-France tramway Line T7]
Generated description
Île-de-France tramway Line T7 is a suburban tram line in the Paris region that connects the southern outskirts, including areas near Orly Airport, to the wider Île-de-France public transport network.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: nearTramwayLine
Context triple: [Chevilly-Larue, nearTramwayLine, Île-de-France tramway Line T7]
  • A. nearestRailwayLine
    Indicates that one railway line is the closest in distance to a given location or feature compared to all other railway lines.
  • B. nearestCommuterRailLine
    Indicates the commuter rail line that is geographically closest to a given location or entity.
  • C. hasNearbyTramStop
    Indicates that a location has a tram stop situated within a short walking distance or close proximity.
  • D. nearUndergroundLine
    Indicates that one entity is located close in distance to an underground (subway/metro) line.
  • E. nearestRailwayTerminus
    Indicates that one location is the closest railway terminus to another specified place.
  • 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_69f348e544a48190ab6e700b05f6438c completed April 30, 2026, 12:19 p.m.
NER Named-entity recognition batch_69f6abe4b214819082e76060f09b4a27 completed May 3, 2026, 1:59 a.m.
NED1 Entity disambiguation (via context triple) batch_6a2d9d5807cc8190b9daf9979bc78747 completed June 13, 2026, 6:11 p.m.
NEDg Description generation batch_6a2d9e0b70308190b161562b869262be completed June 13, 2026, 6:14 p.m.
NED2 Entity disambiguation (via description) batch_6a2da269745c81908e5b582ba3b765c7 completed June 13, 2026, 6:33 p.m.
PD Predicate disambiguation batch_69f6aa21f2508190a204a424ffc00ca6 completed May 3, 2026, 1:51 a.m.
PDg Predicate description generation batch_69f6aac95c1481909fff33702d0a6c37 completed May 3, 2026, 1:54 a.m.
Created at: April 30, 2026, 11:36 p.m.