Triple
T6512235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mo Farah |
E150162
|
entity |
| Predicate | personalBest_halfMarathon |
P71306
|
FINISHED |
| Object | 59:32 |
—
|
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: 59:32 | Statement: [Mo Farah, personalBest_halfMarathon, 59:32]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: personalBest_halfMarathon Context triple: [Mo Farah, personalBest_halfMarathon, 59:32]
-
A.
personalBest
Indicates that one entity represents the best performance or achievement ever attained personally by another entity.
-
B.
marathonWinner
Indicates that one entity is the competitor who finished first and won a specified marathon event.
-
C.
hourRecordDistance
Indicates that one entity holds or represents the record for the greatest distance covered within a one-hour time period relative to another entity or context.
-
D.
hourRecordDistanceKm
Indicates the distance in kilometers that was covered or recorded within a one-hour period.
-
E.
olympicBestResult
Indicates the best performance or highest achievement an entity has attained in Olympic competition.
- 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_69c687ef291081909d437f035eef1cda |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c69f3c5eb88190a56723acd8096dd8 |
completed | March 27, 2026, 3:16 p.m. |
| PD | Predicate disambiguation | batch_69c68ab98c78819081743e614df04e1d |
completed | March 27, 2026, 1:48 p.m. |
| PDg | Predicate description generation | batch_69c69f362ee4819090e8fa48caef7d7d |
completed | March 27, 2026, 3:16 p.m. |
Created at: March 27, 2026, 1:44 p.m.