Triple
T24060470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The China Mission: George Marshall’s Unfinished War, 1945–1947 |
E595934
|
entity |
| Predicate | subjectOfReview |
P61176
|
FINISHED |
| Object | The New York Times |
—
|
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: The New York Times | Statement: [The China Mission: George Marshall’s Unfinished War, 1945–1947, subjectOfReview, The New York Times]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectOfReview Context triple: [The China Mission: George Marshall’s Unfinished War, 1945–1947, subjectOfReview, The New York Times]
-
A.
subjectToReviewProcedure
Indicates that an entity is required to undergo a formal review process or procedure before a decision, approval, or action is finalized.
-
B.
subjectMatter
Indicates the topic, theme, or content area that something (such as a work, document, or discussion) is about.
-
C.
reviewedFor
Indicates that one entity has examined or evaluated another entity for a specific purpose, standard, or context.
-
D.
subjectOfRule
Indicates that an entity is governed, constrained, or described by a particular rule.
-
E.
reviewOf
chosen
Indicates that one entity is a critical or evaluative assessment that is about or directed toward 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_69e288c25c008190850cf447940ab181 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1da55903c8190ad5d578e33a9dae9 |
completed | April 29, 2026, 10:15 a.m. |
| PD | Predicate disambiguation | batch_69f1764b1d4c8190b12590c6339c31c1 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:38 p.m.