Triple
T21248299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liam Costner |
E523674
|
entity |
| Predicate | hasHalfSiblings |
P54212
|
FINISHED |
| Object | children of Kevin Costner from other relationships |
—
|
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: children of Kevin Costner from other relationships | Statement: [Liam Costner, hasHalfSiblings, children of Kevin Costner from other relationships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHalfSiblings Context triple: [Liam Costner, hasHalfSiblings, children of Kevin Costner from other relationships]
-
A.
hasHalfSibling
chosen
Indicates that two individuals share exactly one biological parent in common, making them half-siblings.
-
B.
hasHalfBrother
Indicates that one person has a male sibling with whom they share exactly one biological parent.
-
C.
hasSisters
Indicates that one entity has one or more female siblings in relation to another entity.
-
D.
spouseIsHalfSisterOf
Indicates that the person’s spouse is also their half-sister, sharing exactly one biological parent with them.
-
E.
hasBrothers
Indicates that a person has one or more male siblings.
- 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_69e0b5146c108190adc9adb73e90abff |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7359b756c819085480ca4174c53c2 |
completed | April 21, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69e5f61239708190ab7b3c83ae848a0d |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:55 p.m.