Triple
T9601693
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | softball |
E231864
|
entity |
| Predicate | olympicReturn |
P15215
|
FINISHED |
| Object | returned for Tokyo 2020 Olympics |
—
|
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: returned for Tokyo 2020 Olympics | Statement: [softball, olympicReturn, returned for Tokyo 2020 Olympics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: olympicReturn Context triple: [softball, olympicReturn, returned for Tokyo 2020 Olympics]
-
A.
olympicGames
Indicates that an entity is an edition or instance of the Olympic Games event.
-
B.
OlympicStatus
chosen
Indicates that an entity holds a particular status or role in relation to the Olympic Games (e.g., being an Olympic sport, event, athlete, or host).
-
C.
olympicZone
Indicates a relationship where a location or area is designated as part of an official Olympic zone or territory associated with the Olympic Games.
-
D.
olympicGoldWith
Indicates that the related entities won an Olympic gold medal together, typically as teammates in the same event or competition.
-
E.
openedForOlympics
Indicates that something was opened or inaugurated specifically in preparation for or in conjunction with the Olympic Games.
- 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_69ca8484838c8190b2049199d22fef70 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9a3a49608190ad1f65195e4d5cda |
completed | April 1, 2026, 10:20 p.m. |
| PD | Predicate disambiguation | batch_69ccd5a359788190b24f82399489f7fe |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:07 p.m.