Triple
T33560472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragonwyck |
E859605
|
entity |
| Predicate | EphraimWellsPortrayedBy |
P1507
|
FINISHED |
| Object | Walter Huston |
—
|
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: Walter Huston | Statement: [Dragonwyck, EphraimWellsPortrayedBy, Walter Huston]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: EphraimWellsPortrayedBy Context triple: [Dragonwyck, EphraimWellsPortrayedBy, Walter Huston]
-
A.
dynamicWithEphraimWinslow
Indicates a relationship or interaction involving Ephraim Winslow that is characterized by change, fluctuation, or evolving dynamics over time.
-
B.
friendPortrayedBy
Indicates that a person’s friend is depicted or represented by a particular actor or performer.
-
C.
portrayedBy
chosen
Indicates that one entity serves as the actor or performer who represents or plays the role of another entity in a work or medium.
-
D.
roleOfBen Wells
Indicates the specific role, position, or character that Ben Wells holds or performs in a given context.
-
E.
colleaguePortrayedBy
Indicates that one colleague is depicted or represented by another person, typically in a work or professional context.
- 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_69f3497b2b68819093207971b5e13dc8 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f7127d848190916a5a45fe3b6578 |
completed | May 3, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69f6f6632dfc8190af85e258c8519207 |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:40 a.m.