Triple
T31253087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Wake |
E796882
|
entity |
| Predicate | gaslights |
P23415
|
FINISHED |
| Object | Ephraim Winslow |
—
|
NE NERFINISHED |
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: Ephraim Winslow | Statement: [Thomas Wake, gaslights, Ephraim Winslow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gaslights Context triple: [Thomas Wake, gaslights, Ephraim Winslow]
-
A.
introducedGasLighting
Indicates that one entity initiated or brought the concept, practice, or tactic of gaslighting into use for another entity or within a particular context.
-
B.
isGaslitBy
chosen
Indicates that one entity is being psychologically manipulated by another to make them doubt their own perceptions, memories, or sanity.
-
C.
usedToIlluminate
Indicates that one entity served as a source of light for another entity or environment.
-
D.
gens
Indicates a relationship where one entity generates, produces, or gives rise to another entity.
-
E.
haunts
Indicates that one entity persistently appears in, lingers around, or psychologically troubles another entity or place, often in a recurring or unsettling way.
- 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_69f224dc84d0819081f1cb6f9127e6b1 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d1bf8cc8190a78dfa5ab00daf3a |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:12 p.m.