Triple
T9420655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roy Bryant |
E227140
|
entity |
| Predicate | publicationMention |
P88765
|
FINISHED |
| Object | Look magazine interview about Emmett Till case |
—
|
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: Look magazine interview about Emmett Till case | Statement: [Roy Bryant, publicationMention, Look magazine interview about Emmett Till case]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publicationMention Context triple: [Roy Bryant, publicationMention, Look magazine interview about Emmett Till case]
-
A.
publicationAbout
Indicates that a publication has content whose subject or focus is the referenced entity.
-
B.
publicationType
Indicates the specific category or format of a published work that characterizes how it is issued or presented.
-
C.
publishedIn
Indicates that a work (such as an article, paper, or book) has been formally released or made available within a specific venue, medium, or publication.
-
D.
publicationCollection
Indicates that one entity is a collection or grouping that contains or organizes multiple publication entities.
-
E.
publicationBody
Indicates the organization or entity that serves as the publishing body responsible for issuing the referenced work.
- F. None of above. chosen
Provenance (4 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_69ca84359e7c819091148ba4b670e436 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd6c2528c8819087b0a21e703254b7 |
completed | April 1, 2026, 7:04 p.m. |
| PD | Predicate disambiguation | batch_69cca550777c819094e1851a6127cbbc |
completed | April 1, 2026, 4:55 a.m. |
| PDg | Predicate description generation | batch_69cca89b3368819087a3d69270c1f185 |
completed | April 1, 2026, 5:09 a.m. |
Created at: March 30, 2026, 7:48 p.m.