Triple
T24463314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Jones |
E616894
|
entity |
| Predicate | hasSpouseWork |
P92121
|
FINISHED |
| Object | Aubrey–Maturin series |
—
|
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: Aubrey–Maturin series | Statement: [Elizabeth Jones, hasSpouseWork, Aubrey–Maturin series]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpouseWork Context triple: [Elizabeth Jones, hasSpouseWork, Aubrey–Maturin series]
-
A.
spouseInWork
chosen
Indicates that two entities are spouses within the context of a particular work (such as a book, film, or series), rather than in real life.
-
B.
hasCollaborativeRoleWithSpouse
Indicates that an individual shares a joint, cooperative role or responsibility together with their spouse.
-
C.
hasSpousePositionInFamily
Indicates that a person’s spouse holds a specific role or position within the family structure.
-
D.
spousePlaceOfWork
Indicates that the place of work specified belongs to the spouse of the referenced person.
-
E.
spouseOfWork
Indicates that one person is the spouse of another specifically in the context of their workplace or professional environment.
- F. None of above.
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_69e2d7ef9fe08190a0613908758b4e86 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f298cc60448190a5383d452f563834 |
completed | April 29, 2026, 11:48 p.m. |
| PD | Predicate disambiguation | batch_69f287d76c7c81909494f12e606a9149 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:19 a.m.