Triple
T23210614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jonathan Daniels marker at Virginia Military Institute |
E580581
|
entity |
| Predicate | notesCauseOfDeath |
P138528
|
FINISHED |
| Object | killed while protecting a young Black girl |
—
|
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: killed while protecting a young Black girl | Statement: [Jonathan Daniels marker at Virginia Military Institute, notesCauseOfDeath, killed while protecting a young Black girl]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notesCauseOfDeath Context triple: [Jonathan Daniels marker at Virginia Military Institute, notesCauseOfDeath, killed while protecting a young Black girl]
-
A.
causeOfDeath
Indicates the specific factor, event, or condition that directly resulted in an entity’s death.
-
B.
reasonForDeath
Indicates the cause, circumstance, or condition that led to an entity’s death.
-
C.
namedAfterCauseOfDeath
Indicates that an entity is named after the cause of death of a person or organism.
-
D.
deathDetails
chosen
Indicates the specific circumstances, causes, and contextual information associated with an entity’s death.
-
E.
legendaryCauseOfDeath
Indicates a legendary or mythic account of how an entity died, as opposed to a historically verified cause of death.
- 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_69e24602ae1481908aaa6bc7ca493867 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f191614bc4819080938752d843dcc6 |
completed | April 29, 2026, 5:04 a.m. |
| PD | Predicate disambiguation | batch_69effcccee508190a7ae311fdd319806 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:07 p.m.