Triple
T28566110
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tali David |
E722681
|
entity |
| Predicate | isFictionalSiblingOf |
P116830
|
FINISHED |
| Object | Ziva David |
—
|
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: Ziva David | Statement: [Tali David, isFictionalSiblingOf, Ziva David]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFictionalSiblingOf Context triple: [Tali David, isFictionalSiblingOf, Ziva David]
-
A.
hasFictionalSibling
chosen
Indicates that one entity is a fictional character who is a sibling of another entity.
-
B.
isFictionalTwinOf
Indicates that one entity is the imagined or fictional twin counterpart of another entity, typically within a narrative or creative context.
-
C.
fictionalHalfSibling
Indicates that one entity is considered a half-sibling of another within a fictional or narrative context, sharing one parent in the story’s canon.
-
D.
isLongLostBrotherOf
Indicates that one person is the long-separated, previously unknown or not in contact brother of another person.
-
E.
hasFictionalFamily
Indicates that an entity is associated with a family that exists only within a fictional or imaginary context.
- 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_69f01a5f69d08190ad5c0d2167078dec |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6508ec838819083c24a30f54856e2 |
completed | May 2, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69f64cb0d8008190912e1430cfaf92aa |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 28, 2026, 4:07 a.m.