Triple
T4257383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Pleffer |
E96008
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Gillian Armstrong |
E3085
|
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: Gillian Armstrong | Statement: [John Pleffer, spouse, Gillian Armstrong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gillian Armstrong Context triple: [John Pleffer, spouse, Gillian Armstrong]
-
A.
Gillian Armstrong
chosen
Gillian Armstrong is an Australian film director best known for works such as "My Brilliant Career" and the 1994 adaptation of "Little Women."
-
B.
Jocelyn Moorhouse
Jocelyn Moorhouse is an Australian film director and screenwriter known for character-driven dramas such as "Proof" and "How to Make an American Quilt."
-
C.
Philippa Roet
Philippa Roet was an English courtier of Flemish origin who served in the royal household and is best known as the wife of the poet Geoffrey Chaucer and sister of Katherine Swynford.
-
D.
Susan Ekins
Susan Ekins is a film producer best known for her work on major Hollywood projects, including the heist comedy "Ocean's 8."
-
E.
Deborah Sharp
Deborah Sharp is an American author best known for her humorous Mace Bauer Mystery series set in Florida.
- 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_69b3454095ac81909c2494f7ff294af1 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34ec321008190b2cc1aca6ab690c4 |
completed | March 12, 2026, 11:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5a88d3bf48190b26eb8ab848d320e |
completed | March 14, 2026, 6:27 p.m. |
Created at: March 12, 2026, 11:06 p.m.