Triple
T35806424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | People’s Elbow |
E1035111
|
entity |
| Predicate | performedInRingArea |
P53962
|
FINISHED |
| Object | center of the ring |
—
|
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: center of the ring | Statement: [People’s Elbow, performedInRingArea, center of the ring]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performedInRingArea Context triple: [People’s Elbow, performedInRingArea, center of the ring]
-
A.
facedInRing
Indicates that two competitors directly opposed each other in a formal match or bout, typically within a ring or designated combat area.
-
B.
requiresRingOfficials
Indicates that the event or activity cannot proceed or be valid unless designated ring officials are present or assigned.
-
C.
playedInArena
Indicates that an entity (typically a performer or team) participated in an event that took place within a specific arena.
-
D.
hasRingRegion
Indicates that one entity possesses or includes a ring-shaped region as part of its structure or spatial extent.
-
E.
isOnInnerCircle
chosen
Indicates that one entity belongs to the innermost or most central circle or layer of another 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_69f76e1762408190b885a8456862e372 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff109695008190a22b47ef8be2e3f9 |
completed | May 9, 2026, 10:46 a.m. |
| PD | Predicate disambiguation | batch_69ff0f243ea88190970d2c520b55c816 |
completed | May 9, 2026, 10:40 a.m. |
Created at: May 3, 2026, 4:06 p.m.