Triple
T30190712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AFI's 10 Top 10 Westerns |
E767472
|
entity |
| Predicate | listTopic |
P109559
|
FINISHED |
| Object | greatest Western films in American cinema |
—
|
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: greatest Western films in American cinema | Statement: [AFI's 10 Top 10 Westerns, listTopic, greatest Western films in American cinema]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: listTopic Context triple: [AFI's 10 Top 10 Westerns, listTopic, greatest Western films in American cinema]
-
A.
listsAmong
chosen
Indicates that one entity includes or enumerates another entity as part of a list or collection.
-
B.
listsCategory
Indicates that one entity enumerates or displays the categories to which another entity belongs.
-
C.
listsName
Indicates that an entity presents or enumerates the name of another entity, typically as part of a list or catalog.
-
D.
listType
Indicates that one entity specifies the classification or category type of a list associated with another entity.
-
E.
listAPurpose
Indicates that an entity enumerates or specifies the purposes, goals, or intended uses associated with 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_69f2247cc3d88190811dec3face94bf5 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67f8393948190aa6fc6acea2e7d00 |
completed | May 2, 2026, 10:49 p.m. |
| PD | Predicate disambiguation | batch_69f673c7a4588190837854f3ef61e6bf |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:28 p.m.