Triple
T225413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard Crimson men's ice hockey |
E4303
|
entity |
| Predicate | plays |
P9844
|
FINISHED |
| Object | college ice hockey |
—
|
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: college ice hockey | Statement: [Harvard Crimson men's ice hockey, plays, college ice hockey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plays Context triple: [Harvard Crimson men's ice hockey, plays, college ice hockey]
-
A.
playedAfter
Indicates that one event, performance, or action occurred later in time than another.
-
B.
shows
Indicates that one entity presents, displays, or makes another entity visible or known to an audience or observer.
-
C.
playedWith
Indicates that one entity engaged in play or a playful activity together with another entity.
-
D.
tracks
Indicates that one entity monitors, follows, or keeps a record of another entity’s state, behavior, or progress over time.
-
E.
stage
Indicates that an entity organizes, presents, or performs another entity (such as an event, show, or action) as a staged occurrence.
- F. None of above. chosen
Provenance (4 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_69a257363ffc81909757bde7ab3404da |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25dec53ac8190912f3d79576131fa |
completed | Feb. 28, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69a25b5739dc8190bad8bfa330ce0499 |
completed | Feb. 28, 2026, 3:04 a.m. |
| PDg | Predicate description generation | batch_69a25dea93b48190863a3704b233aa03 |
completed | Feb. 28, 2026, 3:15 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.