Triple
T18383920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kolya |
E446528
|
entity |
| Predicate | relationshipTypeWith Lev Beniov |
P130926
|
FINISHED |
| Object | friendship |
—
|
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: friendship | Statement: [Kolya, relationshipTypeWith Lev Beniov, friendship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWith Lev Beniov Context triple: [Kolya, relationshipTypeWith Lev Beniov, friendship]
-
A.
hasRelationshipTypeWith Alexandra Bergson
Indicates that there exists a specific type or category of relationship between an entity and Alexandra Bergson.
-
B.
relationshipTypeWithJoshSrebnick
Indicates the specific nature or category of the relationship that an entity has with Josh Srebnick.
-
C.
worksInCloseRelationshipWith
Indicates a collaborative professional relationship in which two or more entities work together closely and interact frequently to achieve shared goals.
-
D.
relationshipTypeWithRobertCohn
Indicates the specific nature or category of relationship that an entity has with Robert Cohn.
-
E.
relationshipToBobinot
Indicates the nature or type of relationship that one entity has with Bobinot.
- 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_69d8b9f370b88190b1e5081c2c238e7f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e5179da1048190944398e229e7a4c1 |
completed | April 19, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69e44ff1f92c8190afbb8e85d12bf2a9 |
completed | April 19, 2026, 3:45 a.m. |
| PDg | Predicate description generation | batch_69e451a1bda48190a9cd1db436d4be62 |
completed | April 19, 2026, 3:53 a.m. |
Created at: April 10, 2026, 10:45 a.m.