Triple
T566970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | World Marathon Majors |
E13573
|
entity |
| Predicate | seasonLength |
P8177
|
FINISHED |
| Object | multiple races over a defined cycle |
—
|
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: multiple races over a defined cycle | Statement: [World Marathon Majors, seasonLength, multiple races over a defined cycle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seasonLength Context triple: [World Marathon Majors, seasonLength, multiple races over a defined cycle]
-
A.
seasonDuration
chosen
Indicates the length of time that a particular season lasts.
-
B.
seasonStructure
Indicates how a season is organized or structured in terms of its component parts, phases, or format.
-
C.
competitionSeason
Indicates that an entity is associated with a particular competitive season or edition of a competition.
-
D.
regularSeasonWeeks
Indicates the number of weeks that make up the regular season portion of a schedule or competition.
-
E.
gameLength
Indicates the duration or total length of a game, typically measured in time or turns.
- 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_69a4933edcf08190b35ecfd6014caee6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49b01aca48190944408d066519149 |
completed | March 1, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69a494c183b081909304944aa3d0fe8f |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.