Triple
T33493038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taken at Midnight |
E857789
|
entity |
| Predicate | roleOriginatedBy |
P80506
|
FINISHED |
| Object | Penelope Wilton |
—
|
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: Penelope Wilton | Statement: [Taken at Midnight, roleOriginatedBy, Penelope Wilton]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleOriginatedBy Context triple: [Taken at Midnight, roleOriginatedBy, Penelope Wilton]
-
A.
originAssociatedWith
Indicates a relationship where an entity is connected to, derived from, or influenced by a particular origin, source, or point of beginning.
-
B.
originatesAs
Indicates that one entity begins, arises, or comes into existence in the form, state, or role specified by another entity.
-
C.
originallyBy
Indicates that one entity is the original creator, author, or source of another entity.
-
D.
originPerson
chosen
Indicates that one person is the source, creator, or originating agent of another entity or action.
-
E.
originallyAssociatedWith
Indicates that an entity was first linked, connected, or affiliated with another entity before any later changes in association.
- 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_69f3497547608190a1a0f2365fb713ee |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
Created at: May 1, 2026, 1:38 a.m.