Triple
T38302986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ukraine men’s national gymnastics team |
E1032271
|
entity |
| Predicate | bestOlympicTeamResultEvent |
P33011
|
FINISHED |
| Object | Sydney 2000 men’s team all‑around |
—
|
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: Sydney 2000 men’s team all‑around | Statement: [Ukraine men’s national gymnastics team, bestOlympicTeamResultEvent, Sydney 2000 men’s team all‑around]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bestOlympicTeamResultEvent Context triple: [Ukraine men’s national gymnastics team, bestOlympicTeamResultEvent, Sydney 2000 men’s team all‑around]
-
A.
bestOlympiadResults
Indicates the relationship where an entity holds the highest or most outstanding Olympiad performance or results compared to others.
-
B.
olympicBestResult
chosen
Indicates the best performance or highest achievement an entity has attained in Olympic competition.
-
C.
bestOlympicGamesResultYear
Indicates the year in which an entity achieved its best result at the Olympic Games.
-
D.
olympicGoldMedalInEvent
Indicates that an entity has won an Olympic gold medal in a specified sporting event.
-
E.
medalistAtEvent
Indicates that an entity has won a medal in a specified event.
- 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_69f76e0f2084819091299d021625c3fe |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:30 p.m.