Triple
T26786445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leo Dooley |
E670392
|
entity |
| Predicate | stepsister |
P30827
|
FINISHED |
| Object | Bree Davenport |
—
|
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: Bree Davenport | Statement: [Leo Dooley, stepsister, Bree Davenport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stepsister Context triple: [Leo Dooley, stepsister, Bree Davenport]
-
A.
stepSister
chosen
Indicates that one person is the female child of a parent who is married to, but not the biological or adoptive parent of, another person, making her that person’s stepsister.
-
B.
stepSibling
Indicates that two people share at least one parent but do not share both biological parents, making them step-siblings.
-
C.
sibling
Indicates that two entities share at least one parent, making them brothers or sisters to each other.
-
D.
adoptiveSister
Indicates a sisterly relationship where one person is the sister of another through legal adoption rather than biological parentage.
-
E.
stepCousin
Indicates a familial relationship where one person is the cousin of another through a step-relationship (i.e., connected by marriage rather than by blood).
- 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_69eeb31d45f8819089f52ebdbc556218 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61981c7e08190af1eeedcb257702a |
completed | May 2, 2026, 3:34 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 4:13 a.m.