Triple
T8087209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Villanova Wildcats football |
E188761
|
entity |
| Predicate | programSuspensionEnd |
P51446
|
FINISHED |
| Object | 1984 |
—
|
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: 1984 | Statement: [Villanova Wildcats football, programSuspensionEnd, 1984]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: programSuspensionEnd Context triple: [Villanova Wildcats football, programSuspensionEnd, 1984]
-
A.
supportsSuspension
Indicates that one entity provides the necessary structure, strength, or mechanism to hold or keep another entity suspended.
-
B.
serviceResumed
chosen
Indicates that a previously interrupted or suspended service has been restarted and is functioning again.
-
C.
suspendedIn
Indicates that one entity is held or maintained within another medium or environment without settling or separating.
-
D.
resumedIn
Indicates that an activity, process, or state that was previously paused or interrupted has started again within or at a specified context, time, or location.
-
E.
partiallySuspendedDuring
Indicates that an activity, service, or process is temporarily limited or only partly halted during a specified time or condition, rather than being fully suspended.
- 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_69ca82b662e88190b9323daab8c28a21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4162244481908ab1202a9974deaa |
completed | March 31, 2026, 3:37 a.m. |
| PD | Predicate disambiguation | batch_69cb04a14cd88190a79ed26cbeec1c33 |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:29 p.m.