Triple
T8243437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Warden Hal Moores |
E192790
|
entity |
| Predicate | relatedToTheme |
P56598
|
FINISHED |
| Object | capital punishment |
—
|
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: capital punishment | Statement: [Warden Hal Moores, relatedToTheme, capital punishment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedToTheme Context triple: [Warden Hal Moores, relatedToTheme, capital punishment]
-
A.
followsInTheme
Indicates that one element continues or succeeds another while maintaining the same theme or thematic context.
-
B.
relatedTo
Indicates a general, non-specific relationship or association exists between two entities.
-
C.
followsTheme
Indicates that one entity adheres to, is guided by, or is structured according to the theme established by another entity.
-
D.
associatedWithWorkTheme
chosen
Indicates a relationship where something is connected or related to a particular work theme or subject matter.
-
E.
sharesThemeWith
Indicates that two entities are related by having the same or closely similar underlying theme or subject matter.
- 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_69ca82de7b8c81908d8106f8a53cff9b |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb786f65708190a92ec282b280c813 |
completed | March 31, 2026, 7:31 a.m. |
| PD | Predicate disambiguation | batch_69cb36b437e881909958591357e83b9d |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:47 p.m.