Triple
T9910273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ESTAC Troyes |
E185122
|
entity |
| Predicate | homeStadium |
P890
|
FINISHED |
| Object | Stade de l’Aube |
E185119
|
NE FINISHED |
How this triple was built (2 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: Stade de l’Aube | Statement: [ESTAC Troyes, homeStadium, Stade de l’Aube]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stade de l’Aube Context triple: [ESTAC Troyes, homeStadium, Stade de l’Aube]
-
A.
Stade de l’Aube
chosen
Stade de l’Aube is a football stadium in Troyes, France, primarily known as the home ground of local professional club ES Troyes AC.
-
B.
Stade de l’Abbé-Deschamps
Stade de l’Abbé-Deschamps is a historic football stadium in Auxerre, France, best known as the long-time home ground of Ligue 1 club AJ Auxerre.
-
C.
Stade Malleval
Stade Malleval is a sports stadium in Roanne, France, primarily used for football and other local sporting events.
-
D.
Stade de la Tuilière
Stade de la Tuilière is a modern football stadium in Lausanne, Switzerland, primarily known as the home ground of FC Lausanne-Sport.
-
E.
Stade Marcel-Michelin
Stade Marcel-Michelin is a prominent rugby union stadium in Clermont-Ferrand, France, best known as the long-time home of the Top 14 club ASM Clermont Auvergne.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca8296165881908ca4750701af1f29 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb51184d08190a0350f2722110811 |
completed | April 2, 2026, 12:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2578390888190b60f3962aec37b2d |
completed | April 5, 2026, 12:37 p.m. |
Created at: March 30, 2026, 8:41 p.m.