Triple
T1866159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katie Holmes |
E34925
|
entity |
| Predicate | birthName |
P65
|
FINISHED |
| Object | Kate Noelle Holmes |
E34925
|
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: Kate Noelle Holmes | Statement: [Katie Holmes, birthName, Kate Noelle Holmes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kate Noelle Holmes Context triple: [Katie Holmes, birthName, Kate Noelle Holmes]
-
A.
Katie Holmes
chosen
Katie Holmes is an American actress best known for her role as Joey Potter on the television series "Dawson's Creek" and for her work in film and theater.
-
B.
Anna Watson
Anna Watson is a fictional character known primarily as the rival of Rachel Watson.
-
C.
Holly Rae Taylor
Holly Rae Taylor is an American visual artist and the longtime partner of cartoonist and author Alison Bechdel.
-
D.
Marissa Ribisi
Marissa Ribisi is an American actress known for her roles in films like "Dazed and Confused" and "Pleasantville."
-
E.
Grace Gummer
Grace Gummer is an American actress known for her work in film, television, and theater, including roles in series like "Mr. Robot" and "The Newsroom."
- 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_69a88600b2f88190bc09303e68ab517e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abb0b5978c81909390f2cbd716ccaf |
completed | March 7, 2026, 4:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adf3c82d50819094e8ccdba0faf819 |
completed | March 8, 2026, 10:10 p.m. |
Created at: March 4, 2026, 7:34 p.m.