Triple
T175172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ANZUS |
E3557
|
entity |
| Predicate | hasArticle |
P2947
|
FINISHED |
| Object | collective security clause |
—
|
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: collective security clause | Statement: [ANZUS, hasArticle, collective security clause]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArticle Context triple: [ANZUS, hasArticle, collective security clause]
-
A.
containsArticle
chosen
Indicates that one entity includes or holds an article (such as a written piece, item, or document) as part of its contents.
-
B.
hasPublication
Indicates that an entity is associated with or responsible for a specific publication.
-
C.
articleCount
Indicates the number of articles associated with a given entity or context.
-
D.
hasAuthor
Indicates that an entity is written or created by a specific author.
-
E.
keyArticle
Indicates that an article is a primary or central reference for understanding, supporting, or defining another entity or topic.
- 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_69a25374990081909766d30c79a18e0e |
completed | Feb. 28, 2026, 2:31 a.m. |
| NER | Named-entity recognition | batch_69a258e32da88190ad9485aecd0bf08f |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a25669d99481908c5e82ba8641205a |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:39 a.m.