Triple
T169663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | S (middle initial of Harry S. Truman) |
E3090
|
entity |
| Predicate | reasonForChoice |
P3364
|
FINISHED |
| Object | compromise between names of two grandfathers |
—
|
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: compromise between names of two grandfathers | Statement: [S (middle initial of Harry S. Truman), reasonForChoice, compromise between names of two grandfathers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reasonForChoice Context triple: [S (middle initial of Harry S. Truman), reasonForChoice, compromise between names of two grandfathers]
-
A.
selectionReason
chosen
Indicates the reason or justification for choosing or selecting one entity over alternatives.
-
B.
reasonForReoffer
Indicates the reason or justification for presenting something again after it was previously offered.
-
C.
reasonForRelocation
Indicates the underlying cause, motivation, or circumstance that led an entity to move from one location to another.
-
D.
decisionType
Indicates the specific category or nature of a decision associated with an entity or event.
-
E.
selectionMadeBy
Indicates that a particular choice or selection was performed or decided by a specific agent or 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_69a2524ce1e48190ab066bf72859f474 |
completed | Feb. 28, 2026, 2:26 a.m. |
| NER | Named-entity recognition | batch_69a258b6f4f88190b1264bbbeb19a29e |
completed | Feb. 28, 2026, 2:53 a.m. |
| PD | Predicate disambiguation | batch_69a25665f5b8819096ca3e084faf976e |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:34 a.m.