Triple
T26279255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martin Luther King Jr. |
E660658
|
entity |
| Predicate | wasPronouncedDeadAt |
P33838
|
FINISHED |
| Object | St. Joseph's Hospital, Memphis |
—
|
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: St. Joseph's Hospital, Memphis | Statement: [Martin Luther King Jr., wasPronouncedDeadAt, St. Joseph's Hospital, Memphis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasPronouncedDeadAt Context triple: [Martin Luther King Jr., wasPronouncedDeadAt, St. Joseph's Hospital, Memphis]
-
A.
discoveredAsDeadBy
chosen
Indicates that one entity was found to be dead by another entity, who discovered their deceased state.
-
B.
diedShortlyBefore
Indicates that one entity’s death occurred a brief time before another specified event or entity’s death.
-
C.
wasLeftForDeadBy
Indicates that one entity abandoned another in a life-threatening situation, assuming or intending that the abandoned entity would die.
-
D.
diedAs
Indicates that an entity ceased to live in a particular role, state, or identity.
-
E.
diesAtMomentOf
Indicates that one entity ceases to live precisely at the specific moment or time point associated with another entity or event.
- 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_69ee812960d081909cff6085cc9fa3a6 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60e36ff9c8190843bdf03b6de6b07 |
completed | May 2, 2026, 2:46 p.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 9:58 p.m.