Triple
T27178250
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erin Lindsay |
E683112
|
entity |
| Predicate | hasFosterFather |
P20252
|
FINISHED |
| Object | Hank Voight |
—
|
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: Hank Voight | Statement: [Erin Lindsay, hasFosterFather, Hank Voight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFosterFather Context triple: [Erin Lindsay, hasFosterFather, Hank Voight]
-
A.
hasFosterFamily
Indicates that an entity is placed with and cared for by a foster family, rather than its original or biological family.
-
B.
hasFosterFamilyName
Indicates that an entity has a family name associated with its foster family.
-
C.
fosterParents
chosen
Indicates a relationship where individuals act as temporary parental caregivers for a child who is not their biological or adopted offspring.
-
D.
fosterMother
Indicates a parental relationship where a woman temporarily cares for and raises a child who is not biologically her own, typically through a formal fostering arrangement.
-
E.
hasFatherFigure
Indicates that one entity serves as a paternal or father-like figure to another entity, regardless of biological relation.
- 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_69eefad086808190ab89816c0c300476 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 27, 2026, 9:27 a.m.