Triple
T30370831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European Super Cup 1982 with Aston Villa F.C. |
E772543
|
entity |
| Predicate | firstLegHost |
P88440
|
FINISHED |
| Object | FC Barcelona |
E35595
|
NE 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: FC Barcelona | Statement: [European Super Cup 1982 with Aston Villa F.C., firstLegHost, FC Barcelona]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstLegHost Context triple: [European Super Cup 1982 with Aston Villa F.C., firstLegHost, FC Barcelona]
-
A.
firstLeg
Indicates that one entity represents the initial segment or starting portion of a multi-part journey, sequence, or process involving another entity.
-
B.
firstStageHost
Indicates that an entity serves as the initial host in a multi-stage process or lifecycle involving another entity.
-
C.
secondLegOrigin
Indicates the location from which the second leg of a multi-leg journey or route begins.
-
D.
hostedFirst
chosen
Indicates that one entity acted as the initial host for another entity, preceding any subsequent hosts.
-
E.
firstLocation
Indicates the initial or primary place where an entity is situated, originates, or where an event or relationship begins.
- F. None of above.
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_69f2248d71408190aec0d5c2001b1cff |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a01f4d954e08190aff3756955212d67 |
completed | May 11, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a27ac0a662c8190aac057f859c1762d |
completed | June 9, 2026, 6 a.m. |
| PD | Predicate disambiguation | batch_6a01edadb9248190be592287530740a5 |
completed | May 11, 2026, 2:54 p.m. |
Created at: April 29, 2026, 7:59 p.m.