Triple
T10778469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dené–Caucasian |
E254255
|
entity |
| Predicate | proposesGeneticRelationshipBetween |
P95416
|
FINISHED |
| Object | Eurasian language families |
—
|
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: Eurasian language families | Statement: [Dené–Caucasian, proposesGeneticRelationshipBetween, Eurasian language families]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: proposesGeneticRelationshipBetween Context triple: [Dené–Caucasian, proposesGeneticRelationshipBetween, Eurasian language families]
-
A.
geneticRelation
Indicates that two entities are connected through a hereditary or familial genetic relationship.
-
B.
hasGeneticAffiliation
Indicates that one entity is genetically related or affiliated with another, such as sharing ancestry, lineage, or genetic characteristics.
-
C.
geneticAffinity
Indicates a relationship where entities share a notable degree of genetic similarity or relatedness.
-
D.
hasGenealogicalRelation
Indicates that there exists a family or ancestry-based relationship (such as parent, child, sibling, or more distant kinship) between the related entities.
-
E.
proposedRelationship
Indicates that one entity has suggested or put forward the possibility of entering into a specific type of relationship with another entity.
- F. None of above. chosen
Provenance (4 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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732c25478819093dedec0c8556777 |
completed | April 9, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69d6f31455648190b5c24690487b1b54 |
completed | April 9, 2026, 12:30 a.m. |
| PDg | Predicate description generation | batch_69d6fa334b8c819082eaf8537084c323 |
completed | April 9, 2026, 1 a.m. |
Created at: April 8, 2026, 9:16 p.m.