Triple
T28173811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boston University crew teams |
E715533
|
entity |
| Predicate | useBoatClass |
P88354
|
FINISHED |
| Object | eights |
—
|
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: eights | Statement: [Boston University crew teams, useBoatClass, eights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: useBoatClass Context triple: [Boston University crew teams, useBoatClass, eights]
-
A.
sailingClass
Indicates that one entity is a type or category of sailing activity, vessel, or competition class to which the other entity belongs or is associated.
-
B.
boatTypeAllowed
Indicates that a specified type of boat is permitted or authorized in a given context or location.
-
C.
boatingAllowed
Indicates that operating or using boats is permitted in the specified area or context.
-
D.
boatRaceRole
Indicates the specific role or function an entity has within the context of a boat race (e.g., participant, organizer, official).
-
E.
notableBoatClass
chosen
Indicates that the subject is a notable or significant example of the specified class or type of boat.
- 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_69efd6b340f0819095680e15dcdc1830 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f6423853ec8190892ecc3e097deeb3 |
completed | May 2, 2026, 6:28 p.m. |
| PD | Predicate disambiguation | batch_69f63c6c1a948190b68c0f92c264cc0c |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 10:14 p.m.