Triple
T28022867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alliance Summit |
E707734
|
entity |
| Predicate | reviewFunction |
P163632
|
FINISHED |
| Object | adjust coalition direction as needed |
—
|
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: adjust coalition direction as needed | Statement: [Alliance Summit, reviewFunction, adjust coalition direction as needed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reviewFunction Context triple: [Alliance Summit, reviewFunction, adjust coalition direction as needed]
-
A.
reviewFunction
chosen
Indicates that one entity serves the role or function of reviewing, evaluating, or assessing another entity.
-
B.
reviewType
Indicates the specific category or kind of review associated with an item, action, or relationship.
-
C.
reviewMethod
Indicates the method or process by which something is examined, evaluated, or reviewed.
-
D.
reviewFormat
Indicates the specific structure, style, or medium in which a review is presented or delivered.
-
E.
reviewModel
Indicates that an entity evaluates, critiques, or assesses another entity according to a particular standard or criteria.
- 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_69ef96baf3a881909a2b63844185dddd |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f63fd79e4c8190af9263b679e5ff07 |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 8:11 p.m.