Triple
T13778662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French rugby union championship |
E331078
|
entity |
| Predicate | historicalFormat |
P110916
|
FINISHED |
| Object | knockout tournament |
—
|
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: knockout tournament | Statement: [French rugby union championship, historicalFormat, knockout tournament]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalFormat Context triple: [French rugby union championship, historicalFormat, knockout tournament]
-
A.
historicalForm
Indicates that one entity is an earlier or historically attested form or variant of another entity.
-
B.
formatHistory
Indicates that one entity records or structures the sequence of past states, events, or changes associated with another entity into a specific format.
-
C.
historicalType
Indicates that one entity classifies or characterizes another in terms of its role, status, or category within a historical context.
-
D.
historicalField
Indicates that one entity’s field of study, work, or relevance is situated within the historical domain or concerns past events.
-
E.
historicalDatum
Indicates that something is a specific piece of information or record about a past event, condition, or state.
- F. None of above. chosen
Provenance (4 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_69d81c583b0081909e408a17db517a21 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0239cbfc81909064ac2457fdfff5 |
completed | April 14, 2026, 9 a.m. |
| PD | Predicate disambiguation | batch_69dbbe97846c819093b00ea117b64e0d |
completed | April 12, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69dbc59db0148190bcaf9646403ca64f |
completed | April 12, 2026, 4:17 p.m. |
Created at: April 9, 2026, 10:11 p.m.