Triple
T29861462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hereford United F.C. |
E758328
|
entity |
| Predicate | FAcupUpset |
P6985
|
FINISHED |
| Object | Hereford United 2–1 Newcastle United |
—
|
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: Hereford United 2–1 Newcastle United | Statement: [Hereford United F.C., FAcupUpset, Hereford United 2–1 Newcastle United]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: FAcupUpset Context triple: [Hereford United F.C., FAcupUpset, Hereford United 2–1 Newcastle United]
-
A.
FAcupWinnerWith
Indicates that one entity is the winner of the FA Cup in association with, or in the context of, another specified entity (such as a season, match, or competition instance).
-
B.
hasNotableUpsets
chosen
Indicates that one entity has achieved surprising or unexpected victories over another entity or entities.
-
C.
NCAAFinalRunnerUp
Indicates that an entity finished in second place (as the runner-up) in the NCAA football championship for a given season.
-
D.
cupWins
Indicates that an entity has won a specific cup or tournament competition.
-
E.
notableUpsetYear
Indicates the year in which a notable upset (an unexpected or surprising victory or outcome) occurred.
- 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_69f2245b4dec8190b85f664d918a00a5 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f67685c8c0819089a31631bfba0797 |
completed | May 2, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f66ac32b60819092290b2de35988d3 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 29, 2026, 5:49 p.m.