Triple
T10697070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucy Saroyan |
E252172
|
entity |
| Predicate | notableRelative |
P367
|
FINISHED |
| Object | Carol Grace |
E880797
|
NE FINISHED |
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 Grace | Statement: [Lucy Saroyan, notableRelative, Carol Grace]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carol Grace Context triple: [Lucy Saroyan, notableRelative, Carol Grace]
-
A.
Carol Grace
chosen
Carol Grace was an American actress and author best known for her work on stage and screen and as the wife of playwright William Saroyan and later actor Walter Matthau.
-
B.
Lisa Mann
Lisa Mann is an actress known for her role in the film "Lilies of the Field."
-
C.
Laura Grey
Laura Grey is an American comedian, writer, and actress known for her work on satirical television and sketch comedy, as well as her collaborations with fellow comedian Jordan Klepper.
-
D.
Laila Robins
Laila Robins is an American actress known for her work in film, television, and theater, including roles in series like "Homeland" and "The Boys."
-
E.
Denisia Andrews
Denisia Andrews is a contemporary songwriter best known for co-writing major R&B and pop hits, including Beyoncé’s song “Cuff It.”
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa5cbabc8190973e683950d89faf |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fd89390c8190969ab2b4a79d5818 |
completed | April 9, 2026, 1:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69dbad110d9481908c3c0873424ec616 |
completed | April 12, 2026, 2:32 p.m. |
Created at: April 8, 2026, 9:12 p.m.