Triple
T3847737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Usain Bolt set world records in the 100 m and 200 m sprints |
E85212
|
entity |
| Predicate | medalOutcome |
P32067
|
FINISHED |
| Object | gold medals in both events |
—
|
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: gold medals in both events | Statement: [Usain Bolt set world records in the 100 m and 200 m sprints, medalOutcome, gold medals in both events]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: medalOutcome Context triple: [Usain Bolt set world records in the 100 m and 200 m sprints, medalOutcome, gold medals in both events]
-
A.
medalIn
chosen
Indicates that an entity has received a medal or award in a particular event, field, or competition.
-
B.
medalFor
Indicates that a medal is awarded to an entity in recognition of a specific achievement, action, or service.
-
C.
medalAwardedToWinner
Indicates that a medal is given to the entity that has won a competition or contest.
-
D.
medalType
Indicates the specific category or class of a medal associated with an award or achievement.
-
E.
OlympicMedal
Indicates that an entity has been awarded an Olympic medal in a specific event or discipline.
- 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_69aed936de1c81908f91bed80f70abb2 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeebcc8a0481909c35161336bdfbf9 |
completed | March 9, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69aee750377c8190af70c79768c0edd8 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:18 p.m.