Triple
T20964667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lava and Kusha |
E516335
|
entity |
| Predicate | haveSiblingRelationship |
P363
|
FINISHED |
| Object | twin brothers |
—
|
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: twin brothers | Statement: [Lava and Kusha, haveSiblingRelationship, twin brothers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: haveSiblingRelationship Context triple: [Lava and Kusha, haveSiblingRelationship, twin brothers]
-
A.
siblingOrRelative
Indicates that two entities are related to each other by blood, marriage, or family ties, including but not limited to being siblings.
-
B.
hasSisterRelationshipType
Indicates that there exists a sister-type familial relationship between the related entities.
-
C.
sibling
chosen
Indicates that two entities share at least one parent, making them brothers or sisters to each other.
-
D.
hasHalfSibling
Indicates that two individuals share exactly one biological parent in common, making them half-siblings.
-
E.
hasFamilialTieTo
Indicates a relationship where two entities are connected by family bonds, such as by blood, marriage, or adoption.
- 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_69e0b4fde6c48190af1398e7e734629e |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fb71d644819087e00933fcc26217 |
completed | April 21, 2026, 4:22 a.m. |
| PD | Predicate disambiguation | batch_69e5dbe6976081908abd4e9c8734bae9 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:32 p.m.