Triple
T13119685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | P-Wing |
E311688
|
entity |
| Predicate | persistsUntil |
P106576
|
FINISHED |
| Object | end of level or loss of life |
—
|
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: end of level or loss of life | Statement: [P-Wing, persistsUntil, end of level or loss of life]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: persistsUntil Context triple: [P-Wing, persistsUntil, end of level or loss of life]
-
A.
persistsAfter
Indicates that one state, condition, or effect continues to exist after a specified event, time point, or other state has occurred or ended.
-
B.
persistence
Indicates a continued or repeated existence, occurrence, or effort of something over time despite potential changes or obstacles.
-
C.
supportsPersistence
Indicates that one entity enables or provides the capability for another entity’s data or state to be stored and retained over time.
-
D.
extendsUntil
Indicates that something continues or remains in effect up to a specified point or limit in time or space.
-
E.
heldUntil
chosen
Indicates that a state, condition, or action continues to hold true up to a specified time or event, and may cease to hold immediately after that point.
- 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_69d806a9fe888190b081e2d9ea665d6c |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98196e69081909111407ee3d9f08e |
completed | April 10, 2026, 11:02 p.m. |
| PD | Predicate disambiguation | batch_69d98043a74c81908648e6cd0b4c7f71 |
completed | April 10, 2026, 10:57 p.m. |
Created at: April 9, 2026, 9:06 p.m.