Triple
T32188717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Fowler Jr. |
E822175
|
entity |
| Predicate | featuredInWorkBasedOn |
P193417
|
FINISHED |
| Object | story Killings by Andre Dubus |
—
|
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: story Killings by Andre Dubus | Statement: [Frank Fowler Jr., featuredInWorkBasedOn, story Killings by Andre Dubus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuredInWorkBasedOn Context triple: [Frank Fowler Jr., featuredInWorkBasedOn, story Killings by Andre Dubus]
-
A.
basedOnWorkAppearsIn
chosen
Indicates that one work is derived from or informed by another work in which it appears or is featured.
-
B.
settingOfWorkFeaturedIn
Indicates that a place or environment serves as the primary setting where the events of a creative work take place.
-
C.
workFeatured
Indicates that one work is highlighted, showcased, or given special prominence within a particular context, collection, or presentation.
-
D.
appearsInWorkAbout
Indicates that an entity is mentioned or featured within a work whose subject or focus is that entity.
-
E.
workBy
Indicates that a work (such as a creation, product, or result) is produced, authored, or created by a particular 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_69f3490819cc81909bae1f8ce99423c5 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a00bf5990e08190a8b633e237656564 |
completed | May 10, 2026, 5:24 p.m. |
| PD | Predicate disambiguation | batch_6a00beef4f5881909b00ac89e6af5902 |
completed | May 10, 2026, 5:22 p.m. |
Created at: May 1, 2026, 12:35 a.m.