Triple
T27981625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Giant Haystacks |
E706638
|
entity |
| Predicate | preWrestlingOccupation |
P163603
|
FINISHED |
| Object | labourer |
—
|
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: labourer | Statement: [Giant Haystacks, preWrestlingOccupation, labourer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preWrestlingOccupation Context triple: [Giant Haystacks, preWrestlingOccupation, labourer]
-
A.
trainedWrestlersOn
Indicates that one entity has trained wrestlers on or for another entity, such as a team, organization, or event.
-
B.
wrestlingRole
Indicates the specific capacity or function an individual performs within a wrestling context, such as competitor, referee, coach, or other defined role.
-
C.
promotedWrestler
Indicates that one entity advanced, advertised, or otherwise publicly supported the wrestling career or appearances of another entity.
-
D.
positionInWrestling
Indicates the specific physical hold, stance, or arrangement of wrestlers relative to each other during a wrestling exchange or sequence.
-
E.
wrestledWith
Indicates that one entity engaged in a physical wrestling contest or struggle with another entity.
- 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_69ef96b8b8d88190bad5e4ae966bf14e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f63b693f448190b334a8a505aee5ad |
completed | May 2, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f63893cc188190883ac9321a95d2dc |
completed | May 2, 2026, 5:46 p.m. |
Created at: April 27, 2026, 7:44 p.m.