Triple
T23304582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FC Sion |
E590399
|
entity |
| Predicate | rival |
P437
|
FINISHED |
| Object | Servette FC |
—
|
NE NERFINISHED |
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: Servette FC | Statement: [FC Sion, rival, Servette FC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Servette FC Context triple: [FC Sion, rival, Servette FC]
-
A.
Servette FC
chosen
Servette FC is a historic professional football club from Geneva, Switzerland, known as one of the country’s most successful and traditional teams.
-
B.
FC Sion
FC Sion is a Swiss professional football club from Sion, best known for its strong domestic cup tradition and passionate fan base.
-
C.
Yverdon-Sport FC
Yverdon-Sport FC is a Swiss professional football club based in Yverdon-les-Bains that competes in the country’s league system.
-
D.
FC Stade Nyonnais
FC Stade Nyonnais is a Swiss football club based in the town of Nyon that competes in the national league system.
-
E.
FC Lausanne-Sport
FC Lausanne-Sport is a Swiss professional football club based in Lausanne that competes in the country’s top leagues and has a long-standing presence in national competitions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e25d1c0ecc8190a355aa229f06d0e0 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19725b248819089e61efb82e3440f |
completed | April 29, 2026, 5:29 a.m. |
Created at: April 17, 2026, 5:04 p.m.