Triple
T25576825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joseph Sisko |
E641127
|
entity |
| Predicate | refusesTreatment |
P113186
|
FINISHED |
| Object | prophylactic medication for his heart condition |
—
|
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: prophylactic medication for his heart condition | Statement: [Joseph Sisko, refusesTreatment, prophylactic medication for his heart condition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refusesTreatment Context triple: [Joseph Sisko, refusesTreatment, prophylactic medication for his heart condition]
-
A.
treatmentWithheld
chosen
Indicates that a treatment that could have been provided to an entity was intentionally not administered or was withheld.
-
B.
ultimatelyRefusesToKill
Indicates that an entity, despite prior opportunity or intent, finally decides not to kill another entity.
-
C.
refusesHelpFrom
Indicates that one entity declines or rejects assistance offered by another entity.
-
D.
refusesToLeave
Indicates that an entity is unwilling to depart from a place, situation, or state despite expectation or pressure to do so.
-
E.
refusedDuty
Indicates that an entity declined or failed to accept or perform a duty, task, or responsibility that was expected or assigned.
- 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_69e75dc281bc819095ec04dc0c3a94d0 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f9306d408190b05bc82de8ecfb84 |
completed | May 2, 2026, 1:16 p.m. |
| PD | Predicate disambiguation | batch_69f468421ba08190880eac99135e5970 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 4:01 p.m.