Triple
T29582099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jack Torrance about the hotel’s history |
E753615
|
entity |
| Predicate | warnsAboutCharacter |
P2399
|
FINISHED |
| Object | Delbert Grady |
—
|
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: Delbert Grady | Statement: [Jack Torrance about the hotel’s history, warnsAboutCharacter, Delbert Grady]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: warnsAboutCharacter Context triple: [Jack Torrance about the hotel’s history, warnsAboutCharacter, Delbert Grady]
-
A.
warnsAbout
chosen
Indicates that one entity alerts or cautions another entity about a potential danger, risk, or problem.
-
B.
warningIncludes
Indicates that a warning message or notice contains or encompasses specific information, elements, or details.
-
C.
treatsCharacter
Indicates how one character behaves toward or interacts with another character, especially in terms of care, respect, or mistreatment.
-
D.
hasProtectedCharacter
Indicates that an entity possesses a characteristic or attribute that is legally or formally designated as protected from discrimination or adverse treatment.
-
E.
capturesCharacter
Indicates that one entity seizes, traps, or takes control of another character.
- 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_69f0ef80bf8c8190ad286e99f7df0c63 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f66d7a4460819092b22b56609cc7ed |
completed | May 2, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69f66abfdaf08190a55f14c70be6fd4d |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 6:07 p.m.