Triple

T28100035
Position Surface form Disambiguated ID Type / Status
Subject Congrès de Tours de 1920 E710204 entity
Predicate seTientDans P109650 FINISHED
Object salle du Manège à Tours
La salle du Manège à Tours est un lieu de réunion historique de la ville de Tours, notamment connu pour avoir accueilli le Congrès de Tours de 1920, moment clé de l’histoire politique française.
 E1803162 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: salle du Manège à Tours | Statement: [Congrès de Tours de 1920, seTientDans, salle du Manège à Tours]
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: salle du Manège à Tours
Triple: [Congrès de Tours de 1920, seTientDans, salle du Manège à Tours]
Generated description
La salle du Manège à Tours est un lieu de réunion historique de la ville de Tours, notamment connu pour avoir accueilli le Congrès de Tours de 1920, moment clé de l’histoire politique française.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: seTientDans
Context triple: [Congrès de Tours de 1920, seTientDans, salle du Manège à Tours]
  • A. appartientÀ
    Indicates that one entity belongs to, is a member of, or is part of another entity.
  • B. locatedInTheInteriorOf chosen
    Indicates that one entity is situated entirely within the inner part or inside area of another entity, rather than on its surface or boundary.
  • C. hasPartIn
    Indicates that an entity participates in or plays a role within a larger event, process, or composite entity.
  • D. sometimesLocatedIn
    Indicates that an entity is located in a given place only at certain times or under certain conditions, rather than permanently or always.
  • E. situéeDansLeDépartement
    Indicates that one entity is located within the administrative boundaries of a specific department.
  • 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_69ef9b70fd108190a875953b2e50ca91 completed April 27, 2026, 5:22 p.m.
NER Named-entity recognition batch_69f640908b208190857b085879e60e1c completed May 2, 2026, 6:21 p.m.
NED1 Entity disambiguation (via context triple) batch_6a15c926cd0881909ae1aa3d39512418 completed May 26, 2026, 4:24 p.m.
NEDg Description generation batch_6a15cd324ba8819090478ecef40017ea completed May 26, 2026, 4:41 p.m.
NED2 Entity disambiguation (via description) batch_6a15ce365de4819098362b1376950217 completed May 26, 2026, 4:45 p.m.
PD Predicate disambiguation batch_69f63c6a8474819091b8c6fe98e3862d completed May 2, 2026, 6:03 p.m.
Created at: April 27, 2026, 9:04 p.m.