Triple
T32510054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Croft family |
E830906
|
entity |
| Predicate | hasFamilyMemberOccupation |
P26374
|
FINISHED |
| Object | archaeologist |
—
|
LITERAL 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: archaeologist | Statement: [Croft family, hasFamilyMemberOccupation, archaeologist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFamilyMemberOccupation Context triple: [Croft family, hasFamilyMemberOccupation, archaeologist]
-
A.
siblingOccupation
Indicates that one person has a sibling whose job or profession is the specified occupation.
-
B.
parentOccupation
Indicates that one entity has an occupation which is the job or profession of the other entity’s parent.
-
C.
knownRelativesOccupation
chosen
Indicates that there is information about the occupations held by one or more relatives of a given person.
-
D.
hasFamilyRelationInWork
Indicates that there exists a family relationship between two entities within the context of a specific work (e.g., book, film, or other creative work).
-
E.
employedByFamily
Indicates that a person is employed in a job or role by a family member or a family-owned entity.
- 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_69f3492318348190ba37fb6b5f1d67f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd44474ed48190ac372e4c88d762ed |
completed | May 8, 2026, 2:02 a.m. |
| PD | Predicate disambiguation | batch_69fd41ef28a48190a66959be5c964461 |
completed | May 8, 2026, 1:52 a.m. |
Created at: May 1, 2026, 1 a.m.