Triple
T16248698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tippi Hedren |
E394440
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Peter Griffith |
E738904
|
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: Peter Griffith | Statement: [Tippi Hedren, spouse, Peter Griffith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Griffith Context triple: [Tippi Hedren, spouse, Peter Griffith]
-
A.
Peter Griffith
chosen
Peter Griffith is an American advertising executive and the father of actress Melanie Griffith and grandfather of actress Dakota Johnson.
-
B.
Chris Grant
Chris Grant is a professional choreographer best known for creating dance routines for major pop artists, including work on Beyoncé’s tours.
-
C.
Gene Griffin
Gene Griffin is an American R&B and new jack swing record producer and manager best known for his work with acts like Guy and Bobby Brown.
-
D.
Darren McGavin
Darren McGavin was an American actor best known for his roles in the television series "Kolchak: The Night Stalker" and as the gruff but loving father in the classic film "A Christmas Story."
-
E.
Martin Mull
Martin Mull is an American actor, comedian, and musician known for his dry wit and roles in television comedies and films.
- 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_69d87f2171208190951025e526947816 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e24594f23c8190bd59fcb2585cb5e3 |
completed | April 17, 2026, 2:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a000ee3bbc48190a56ce2807a9510f0 |
completed | May 10, 2026, 4:51 a.m. |
Created at: April 10, 2026, 5:04 a.m.