Triple
T20543588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States at the 1996 Summer Olympics |
E504407
|
entity |
| Predicate | womenGymnasticsTeamEvent |
P13104
|
FINISHED |
| Object | women's artistic 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: women's artistic team all-around | Statement: [United States at the 1996 Summer Olympics, womenGymnasticsTeamEvent, women's artistic team all-around]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: womenGymnasticsTeamEvent Context triple: [United States at the 1996 Summer Olympics, womenGymnasticsTeamEvent, women's artistic team all-around]
-
A.
womenTeam
chosen
Indicates that the team is composed of women or is designated as a women’s team.
-
B.
womenTeamSilver
Indicates that a women’s team achieved second place and was awarded the silver medal in a competition or event.
-
C.
gymnasticsStar
Indicates that one entity is recognized as an outstanding or star performer in gymnastics.
-
D.
womenUnevenBarsChampion
Indicates that the subject is the champion in a women's uneven bars gymnastics event or competition.
-
E.
conferenceGymnastics
Indicates a relationship where a conference is focused on, features, or is associated with gymnastics activities or events.
- 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_69e0b4b476648190bc6019622ae54d3c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a293feac8190b27848b64f2db1fe |
completed | April 20, 2026, 10:03 p.m. |
| PD | Predicate disambiguation | batch_69e59fe5592c8190bb6122b784496d02 |
completed | April 20, 2026, 3:39 a.m. |
Created at: April 16, 2026, 11:38 a.m.