Triple
T2578118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bancor |
E57023
|
entity |
| Predicate | debatedWithAlternativePlan |
P40372
|
FINISHED |
| Object | Harry Dexter White plan |
—
|
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: Harry Dexter White plan | Statement: [Bancor, debatedWithAlternativePlan, Harry Dexter White plan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: debatedWithAlternativePlan Context triple: [Bancor, debatedWithAlternativePlan, Harry Dexter White plan]
-
A.
compromisePlan
Indicates that an entity develops, proposes, or adopts a plan intended to reconcile conflicting positions or interests between parties.
-
B.
couldConsider
Indicates that one entity has the potential or option to take another entity into account when making a decision, judgment, or evaluation.
-
C.
debatedAsCauseOf
Indicates that one entity is discussed or argued over as a possible cause or origin of another entity.
-
D.
debatedAt
Indicates that a debate or formal discussion involving the subject took place at the specified location or event.
-
E.
reargued
Indicates that an argument, case, or issue was presented and debated again, typically after having been argued previously.
- 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_69ab4a4dca6481908c301f8e317396e7 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd3a86f9881908df29a7caaf9a7df |
completed | March 7, 2026, 7:28 a.m. |
| PD | Predicate disambiguation | batch_69abd0cfeae08190aed03866ba071c5c |
completed | March 7, 2026, 7:16 a.m. |
| PDg | Predicate description generation | batch_69abd209d934819093600889af9104c3 |
completed | March 7, 2026, 7:21 a.m. |
Created at: March 6, 2026, 9:49 p.m.