Triple
T18183090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epsom Derby Festival |
E435338
|
entity |
| Predicate | hasInfieldEvent |
P44792
|
FINISHED |
| Object | funfair and entertainment for spectators |
—
|
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: funfair and entertainment for spectators | Statement: [Epsom Derby Festival, hasInfieldEvent, funfair and entertainment for spectators]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInfieldEvent Context triple: [Epsom Derby Festival, hasInfieldEvent, funfair and entertainment for spectators]
-
A.
hasInfield
Indicates that an entity possesses or includes a designated infield area, typically within a larger spatial or structural context.
-
B.
hasInfieldOval
Indicates that one entity possesses or includes an oval-shaped infield area as part of its structure or layout.
-
C.
hasSideEvent
chosen
Indicates that an event is associated with an additional, related side event occurring alongside it.
-
D.
hasNameInEvent
Indicates that an entity is associated with a specific name or label within the context of a particular event.
-
E.
hasFireEvent
Indicates that a fire-related incident or occurrence is associated with, or has taken place involving, a given entity.
- 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_69d8b90c7ec081909b4694ccecb449c6 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4dffc432c8190af53da5256dc476c |
completed | April 19, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69e4331e92408190ad607ba4956a3897 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:31 a.m.