Triple
T28520006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elmo Blatch |
E721733
|
entity |
| Predicate | workAdaptationDirector |
P73872
|
FINISHED |
| Object | Frank Darabont |
—
|
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: Frank Darabont | Statement: [Elmo Blatch, workAdaptationDirector, Frank Darabont]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workAdaptationDirector Context triple: [Elmo Blatch, workAdaptationDirector, Frank Darabont]
-
A.
hasAdaptationDirector
chosen
Indicates that an adaptation (such as a film, series, or other derivative work) is directed or overseen by a specific director.
-
B.
workAdaptedFor
Indicates that one work has been modified or transformed to create another work specifically suited for a different medium, context, or audience.
-
C.
workDirector
Indicates that one entity serves as the director (creative or managerial lead) of a particular work or production associated with the other entity.
-
D.
workAdaptedIn
Indicates that a work has been transformed or re-created into another medium or format, such as a book adapted into a film, play, or other derivative work.
-
E.
workFeaturedDirector
Indicates that a work prominently features or highlights a particular director, typically as a key creative contributor.
- 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_69f01a5cbcc4819083fb4e723378713e |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f64fa169e48190b061b3b3014a079d |
completed | May 2, 2026, 7:25 p.m. |
| PD | Predicate disambiguation | batch_69f64cb0d8008190912e1430cfaf92aa |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 28, 2026, 3:20 a.m.