Triple
T33951409
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | women's 100 metres hurdles |
E870449
|
entity |
| Predicate | ageCategoryAtSeniorLevel |
P144158
|
FINISHED |
| Object | senior |
—
|
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: senior | Statement: [women's 100 metres hurdles, ageCategoryAtSeniorLevel, senior]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ageCategoryAtSeniorLevel Context triple: [women's 100 metres hurdles, ageCategoryAtSeniorLevel, senior]
-
A.
ageBased
Indicates a relationship or condition that depends on or is determined by the age of the entities involved.
-
B.
isSeniorTo
Indicates that one entity holds a higher rank, status, or level of authority than another.
-
C.
ageRetired
Indicates the age at which an entity stopped working in their primary occupation or officially retired.
-
D.
ageRangeUpper
Indicates the maximum age limit that bounds the upper end of an age range associated with an entity or relationship.
-
E.
ageCategoryDefinition
chosen
Indicates the rule or criteria that define how ages are grouped into specific age categories.
- 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_69f3499c2d7481909c953a5010227725 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:49 a.m.