Triple
T27206980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wang Junxia |
E683890
|
entity |
| Predicate | athleticDiscipline |
P50990
|
FINISHED |
| Object | track long-distance running |
—
|
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: track long-distance running | Statement: [Wang Junxia, athleticDiscipline, track long-distance running]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: athleticDiscipline Context triple: [Wang Junxia, athleticDiscipline, track long-distance running]
-
A.
sportDisciplineScope
Indicates the specific sport discipline or category within which a given relationship, rule, or activity is defined or applies.
-
B.
esportDiscipline
Indicates that one entity is a specific esports game or discipline in which the other entity participates or is involved.
-
C.
hasOlympicDiscipline
chosen
Indicates that an entity (typically a sport) includes or is associated with a specific discipline as recognized in the Olympic Games.
-
D.
olympicEventType
Indicates the specific category or discipline of an event within the Olympic Games.
-
E.
WorldCupDiscipline
Indicates a disciplinary action (such as a card, suspension, or sanction) imposed on an entity in the context of a FIFA World Cup competition.
- 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_69eefad339a08190aeacb2a198f1a39b |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f625e6138c819093137c0d085b499b |
completed | May 2, 2026, 4:27 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 9:38 a.m.