Triple
T36946635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tyson Gay |
E913929
|
entity |
| Predicate | personalBestTimeIn100Metres |
P186763
|
FINISHED |
| Object | 9.69 s |
—
|
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: 9.69 s | Statement: [Tyson Gay, personalBestTimeIn100Metres, 9.69 s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: personalBestTimeIn100Metres Context triple: [Tyson Gay, personalBestTimeIn100Metres, 9.69 s]
-
A.
personalBest400m
Indicates that the related 400-meter race performance is the best time or result the person has ever achieved in that event.
-
B.
personalBest800m
Indicates that an entity holds or represents a person's best performance or fastest recorded time in the 800-meter event.
-
C.
personalBest60m
Indicates that an entity has achieved its best-ever performance or record time in a 60-meter event.
-
D.
personalBest400mDate
Indicates the date on which an entity achieved its personal best performance in the 400-meter event.
-
E.
worldRecordTime
Indicates that an entity’s recorded time for an event is the fastest ever achieved globally, i.e., the official world record time for that event.
- F. None of above. chosen
Provenance (4 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_69f76e8b28848190abd81fe7a7374910 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fa0a7b00948190a257273d9968c5d7 |
completed | May 5, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69f9fec9c9488190ae2a349651a02782 |
completed | May 5, 2026, 2:29 p.m. |
| PDg | Predicate description generation | batch_69fa0a799b9081909bfa8293a22c4b00 |
completed | May 5, 2026, 3:19 p.m. |
Created at: May 3, 2026, 4:13 p.m.