Triple
T17644891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Suzy Izzard |
E429328
|
entity |
| Predicate | marathonAchievement |
P128376
|
FINISHED |
| Object | 43 marathons in 51 days for Sport Relief (2009) |
—
|
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: 43 marathons in 51 days for Sport Relief (2009) | Statement: [Suzy Izzard, marathonAchievement, 43 marathons in 51 days for Sport Relief (2009)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marathonAchievement Context triple: [Suzy Izzard, marathonAchievement, 43 marathons in 51 days for Sport Relief (2009)]
-
A.
marathonWinner
Indicates that one entity is the competitor who finished first and won a specified marathon event.
-
B.
personalBestMarathon
Indicates that the associated marathon performance is the best (fastest or highest-achieving) marathon result attained by the person in question.
-
C.
personalBestMarathonYear
Indicates the year in which an entity achieved their personal best performance in a marathon.
-
D.
runsTheLengthOf
Indicates that one entity extends continuously alongside or across the full distance of another entity.
-
E.
personalBest_halfMarathon
Indicates that the associated half marathon performance is the best (fastest or highest-achieving) one recorded for the person.
- 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_69d889e2c2608190b762e76d9b2262f1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46e382ba88190af19d0e3b8c8cadd |
completed | April 19, 2026, 5:55 a.m. |
| PD | Predicate disambiguation | batch_69e3cddc87188190ac2f049b86038676 |
completed | April 18, 2026, 6:30 p.m. |
| PDg | Predicate description generation | batch_69e3cfaac2b881909e1140339eb1a0dd |
completed | April 18, 2026, 6:38 p.m. |
Created at: April 10, 2026, 6:04 a.m.