Triple
T3379619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IAAF World Championships Marathon |
E71149
|
entity |
| Predicate | firstHeldAsPartOfWorldChampionships |
P27044
|
FINISHED |
| Object | 1983 |
—
|
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: 1983 | Statement: [IAAF World Championships Marathon, firstHeldAsPartOfWorldChampionships, 1983]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstHeldAsPartOfWorldChampionships Context triple: [IAAF World Championships Marathon, firstHeldAsPartOfWorldChampionships, 1983]
-
A.
firstHeldAsWorldChampionshipRound
chosen
Indicates the event or race at which a competition was first officially held as a round of the world championship.
-
B.
WorldChampionshipParticipation
Indicates that an entity has taken part in a world championship event or competition.
-
C.
firstHeldAsSeparateTournament
Indicates that an event was initially conducted as an independent, standalone tournament rather than as part of another competition.
-
D.
championshipHeldIn
Indicates that a particular championship event takes place or is hosted in a specific location.
-
E.
WorldChampionshipAppearances
Indicates the number of times an entity has participated in a world championship competition.
- 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_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2ec38d88190be8c824daeca5ab6 |
completed | March 8, 2026, 5:33 p.m. |
| PD | Predicate disambiguation | batch_69ada434bae48190a77ea37f9274ad8f |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:14 p.m.