Triple
T29890815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Alphabet Murders |
E759144
|
entity |
| Predicate | characterInAdaptation |
P106159
|
FINISHED |
| Object | Hercule Poirot |
—
|
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: Hercule Poirot | Statement: [The Alphabet Murders, characterInAdaptation, Hercule Poirot]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterInAdaptation Context triple: [The Alphabet Murders, characterInAdaptation, Hercule Poirot]
-
A.
adaptationOfCharacterFrom
Indicates that one character is derived, modified, or reinterpreted from an existing character in another work or version.
-
B.
characterIn
Indicates that an entity appears as a character within a specified work, story, or narrative.
-
C.
filmCharacterVersionOf
Indicates that one character is a specific film adaptation or portrayal of another character originating from a different version or medium.
-
D.
portrayedInAdaptationOf
chosen
Indicates that an entity is depicted as a character or role within an adaptation (such as a film, series, or game) that is based on another original work.
-
E.
creatorOfAdaptationCharacterIn
Indicates that a person is the creator of a character that appears in a particular adaptation of a work.
- 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_69f2245f1cf88190978c70d1a1d2cb73 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fd974d75e08190af46b1d608769f3b |
completed | May 8, 2026, 7:57 a.m. |
| PD | Predicate disambiguation | batch_69fd94ff792c8190bedf4a639d3da809 |
completed | May 8, 2026, 7:47 a.m. |
Created at: April 29, 2026, 6:02 p.m.