Triple
T20004710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Lawrence |
E494423
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Christa Miller |
—
|
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: Christa Miller | Statement: [Bill Lawrence, spouse, Christa Miller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Christa Miller Context triple: [Bill Lawrence, spouse, Christa Miller]
-
A.
Christa Miller
chosen
Christa Miller is an American actress best known for her comedic television roles, including prominent parts on series like Scrubs and Cougar Town.
-
B.
Mary Miller
Mary Miller is an American art historian and archaeologist renowned for her scholarship on Mesoamerican, particularly Maya, art and culture.
-
C.
Mary Beth Johnson
Mary Beth Johnson is known as the wife of American Western film actor Charles Starrett.
-
D.
Ana Miller
Ana Miller is a supporting character in the 2018 film "Tomb Raider," serving as a close associate of the Croft family who becomes involved in the aftermath of Richard Croft’s disappearance.
-
E.
Lorraine Miller
Lorraine Miller was an American actress and dancer active in Hollywood films during the 1940s and 1950s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a46c748190a141ab5aac6ea250 |
completed | April 20, 2026, 5:25 p.m. |
Created at: April 11, 2026, 3:33 p.m.