Triple
T120573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boston Marathon |
E2435
|
entity |
| Predicate | spectators |
P1347
|
FINISHED |
| Object | hundreds of thousands of spectators along the course |
—
|
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: hundreds of thousands of spectators along the course | Statement: [Boston Marathon, spectators, hundreds of thousands of spectators along the course]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spectators Context triple: [Boston Marathon, spectators, hundreds of thousands of spectators along the course]
-
A.
sponsors
Indicates that one entity provides financial or material support to another, often in exchange for association, promotion, or fulfillment of certain activities or goals.
-
B.
sponsorSport
Indicates that one entity financially or materially supports a sport or sporting activity, typically in exchange for promotion or association.
-
C.
stadium
Indicates that an entity is a sports or event venue where games, competitions, or large gatherings take place.
-
D.
attracts
chosen
Indicates that one entity exerts a force or influence that draws another entity toward it.
-
E.
overlooks
Indicates that one entity has a view toward or looks out over another entity, typically from a higher or adjacent position.
- 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_69a2506c5428819085c28a8884790e29 |
completed | Feb. 28, 2026, 2:18 a.m. |
| NER | Named-entity recognition | batch_69a258fd278481908ad4498e03f38e2f |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a25647fe6081908cb0405266d35ff5 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:24 a.m.