Triple
T27086998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | World Championships (Greco-Roman wrestling) |
E686060
|
entity |
| Predicate | matSurface |
P1242
|
FINISHED |
| Object | wrestling mat |
—
|
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: wrestling mat | Statement: [World Championships (Greco-Roman wrestling), matSurface, wrestling mat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: matSurface Context triple: [World Championships (Greco-Roman wrestling), matSurface, wrestling mat]
-
A.
surfaceRecord
Indicates that an entity documents or presents information about the external aspects or observable features of another entity or phenomenon.
-
B.
capSurface
Indicates that one entity serves as the top or end surface (a cap) enclosing or terminating another entity.
-
C.
surfaceType
chosen
Indicates the kind or classification of surface associated with an entity or interaction.
-
D.
targetSurface
Indicates the surface or area that an action, effect, or object is directed at or intended to impact.
-
E.
apiSurface
Indicates the set of publicly exposed functions, classes, endpoints, or interfaces that define how external code or systems can interact with an API.
- 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_69ef148940ec819097b5c20fbfbf7c81 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f6234735cc819097c3f109e724b0a4 |
completed | May 2, 2026, 4:16 p.m. |
| PD | Predicate disambiguation | batch_69f61b40f02081909bd9c3ea73249163 |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 8:38 a.m.