Triple
T37376125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walt Berkman |
E927985
|
entity |
| Predicate | adaptsBehaviorFrom |
P153409
|
FINISHED |
| Object | Bernard Berkman |
—
|
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: Bernard Berkman | Statement: [Walt Berkman, adaptsBehaviorFrom, Bernard Berkman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adaptsBehaviorFrom Context triple: [Walt Berkman, adaptsBehaviorFrom, Bernard Berkman]
-
A.
adaptsFrom
Indicates that one entity is derived, modified, or transformed from another, preserving core elements while changing form, medium, or context.
-
B.
adaptsBy
Indicates that one entity changes, modifies, or adjusts itself, its behavior, or its form as a result of influence, guidance, or transformation performed by another entity.
-
C.
affectsBehaviorOf
chosen
Indicates that one entity produces a change or influence on the behavior, actions, or conduct of another entity.
-
D.
targetBehaviorChange
Indicates a relationship where an intervention or influence is intended to alter, modify, or redirect an entity’s behavior from its current state to a desired new state.
-
E.
advisedBehavior
Indicates that one entity recommends or counsels a particular behavior or course of action to another entity.
- 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_69f76eb820248190a5c395ca50ad002a |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb9e1845e881908d19158440cf3b87 |
completed | May 6, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69fb8d08d6988190a00794ac26078348 |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:16 p.m.