Triple
T435486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Proctor |
E10001
|
entity |
| Predicate | legalStatusAtDeath |
P7958
|
FINISHED |
| Object | convicted of witchcraft |
—
|
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: convicted of witchcraft | Statement: [John Proctor, legalStatusAtDeath, convicted of witchcraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalStatusAtDeath Context triple: [John Proctor, legalStatusAtDeath, convicted of witchcraft]
-
A.
martyrdomStatus
Indicates the state or condition of an entity with respect to being recognized or regarded as a martyr.
-
B.
criminalStatus
chosen
Indicates the legal condition of an entity with respect to criminal law, such as whether they are accused, convicted, or cleared of a crime.
-
C.
causeOfDeath
Indicates the specific factor, event, or condition that directly resulted in an entity’s death.
-
D.
dateOfDeath
Indicates the specific date on which an individual or entity died.
-
E.
diedWhile
Indicates that one entity ceased to live during the occurrence or performance of another specified event or activity.
- 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_69a2e8465ef481909655c681b01e2986 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2ef0b6e0c8190ad6a335ee804829c |
completed | Feb. 28, 2026, 1:35 p.m. |
| PD | Predicate disambiguation | batch_69a2eddb98e081909efcf9f0a955a908 |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.