Triple
T35313603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toulouse Olympique |
E1019842
|
entity |
| Predicate | hasHistoricalLeague |
P91391
|
FINISHED |
| Object | French domestic competitions |
—
|
LITERAL 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: French domestic competitions | Statement: [Toulouse Olympique, hasHistoricalLeague, French domestic competitions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHistoricalLeague Context triple: [Toulouse Olympique, hasHistoricalLeague, French domestic competitions]
-
A.
hasHistoricFranchise
Indicates that an entity is associated with or possesses a franchise that has historical significance or longstanding legacy.
-
B.
historicLeagueStatus
chosen
Indicates that an entity’s league affiliation or classification applied in the past (historically), rather than reflecting its current league status.
-
C.
hasCompetitionHistory
Indicates that an entity has a recorded history of participation in competitions or competitive events.
-
D.
hasNonLeagueFootballHistory
Indicates that an entity has a history of participation in football competitions outside the official league system.
-
E.
hasHistoricalData
Indicates that an entity possesses recorded information or records about past events, states, or values relevant to it.
- F. None of above.
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_69f76de9d45c81908a2ed0956b448b65 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff3fb2318c81908a46c2f513608935 |
completed | May 9, 2026, 2:07 p.m. |
| PD | Predicate disambiguation | batch_69ff3e96dcc48190819f6204680d84aa |
completed | May 9, 2026, 2:03 p.m. |
Created at: May 3, 2026, 4:03 p.m.