Triple
T31308990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emmett Till |
E798410
|
entity |
| Predicate | victimOfAccusationsBy |
P54285
|
FINISHED |
| Object | Carolyn Bryant Donham |
—
|
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: Carolyn Bryant Donham | Statement: [Emmett Till, victimOfAccusationsBy, Carolyn Bryant Donham]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: victimOfAccusationsBy Context triple: [Emmett Till, victimOfAccusationsBy, Carolyn Bryant Donham]
-
A.
victimOfAccusation
Indicates that an entity is the target or subject of an accusation made by another party.
-
B.
allegedVictimOf
Indicates that one entity is claimed or reported to have been harmed, wronged, or victimized by another entity, without asserting that the claim is proven.
-
C.
accusedIn
Indicates that a person or entity is formally charged with wrongdoing in a particular case, proceeding, or context.
-
D.
accusationTarget
chosen
Indicates that one entity is the object or recipient of an accusation made by another entity.
-
E.
coAccusedInCaseWith
Indicates that two or more entities are jointly accused as defendants in the same legal case.
- 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_69f224e1932c81908fef14f7b03a10b7 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6a916d2e08190bafc01cba73b6469 |
completed | May 3, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69f6a7548eb48190a69b60a3c6ad53b9 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 29, 2026, 9:15 p.m.