Triple
T3528941
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andy Bernard |
E74608
|
entity |
| Predicate | positionChange |
P49285
|
FINISHED |
| Object | from salesman to regional manager |
—
|
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: from salesman to regional manager | Statement: [Andy Bernard, positionChange, from salesman to regional manager]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionChange Context triple: [Andy Bernard, positionChange, from salesman to regional manager]
-
A.
positionOn
Indicates that one entity is located on top of or at a specific place along the surface or extent of another entity.
-
B.
positionB
Indicates that one entity occupies or is located at a specific position relative to another entity.
-
C.
alignmentChange
Indicates a change in the moral, ethical, or factional stance of an entity relative to its previous alignment.
-
D.
positionInCase
Indicates the specific role, status, or placement that an entity holds within a particular case or legal proceeding.
-
E.
positionA
Indicates the spatial or ordered position of an entity A within a defined reference frame or sequence.
- 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_69ad85d1a3948190931fd1ea1f49717b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbc6e9188819093480b39f263ce75 |
completed | March 8, 2026, 6:14 p.m. |
| PD | Predicate disambiguation | batch_69adae121a048190b03825a001d21f49 |
completed | March 8, 2026, 5:12 p.m. |
| PDg | Predicate description generation | batch_69adb21a437c81908bca88d5e123d744 |
completed | March 8, 2026, 5:30 p.m. |
Created at: March 8, 2026, 3:19 p.m.