Triple
T30612664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Bernstein |
E779221
|
entity |
| Predicate | motherPortrayedCharacter |
P61229
|
FINISHED |
| Object | Carol Brady |
—
|
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: Carol Brady | Statement: [Robert Bernstein, motherPortrayedCharacter, Carol Brady]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: motherPortrayedCharacter Context triple: [Robert Bernstein, motherPortrayedCharacter, Carol Brady]
-
A.
motherPortrayedBy
chosen
Indicates that a person’s mother is depicted or played by a particular actor or performer.
-
B.
characterPortrayedIs
Indicates that one entity serves as the fictional or dramatic role that is depicted or played by another entity.
-
C.
sonCharacterPortrayedBy
Indicates that a person is the actor who portrays a specific son character in a work of fiction.
-
D.
friendPortrayedBy
Indicates that a person’s friend is depicted or represented by a particular actor or performer.
-
E.
motherCharacterBasedOn
Indicates that one mother character is created or written based on another specific 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_69f224a3307081909a6dca8ca75dbf48 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68a16debc8190a12f5f65ced055d7 |
completed | May 2, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_69f6860def1c81909d79e1f088c4b5e5 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:26 p.m.