Triple
T1247583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prayer of Manasseh |
E26801
|
entity |
| Predicate | closingMotive |
P8451
|
FINISHED |
| Object | petition for pardon |
—
|
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: petition for pardon | Statement: [Prayer of Manasseh, closingMotive, petition for pardon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closingMotive Context triple: [Prayer of Manasseh, closingMotive, petition for pardon]
-
A.
closingSituation
Indicates a situation or context in which an interaction, event, or process is coming to an end or being brought to a close.
-
B.
closureReason
chosen
Indicates the reason or cause for which an entity, process, or case has been closed or terminated.
-
C.
closingFeatures
Indicates that an entity has specific characteristics, terms, or attributes associated with the act or process of closing (e.g., ending, shutting down, or finalizing something).
-
D.
closingSection
Indicates that one entity serves as the concluding or final section of another entity (such as a document, event, or structured sequence).
-
E.
closedUnder
Indicates that applying a specified operation to elements within a set always produces a result that is also an element of that same set.
- 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_69a49487a9c48190ba9b05348fd1b53f |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4bf6750a48190b86e9248ed54d90a |
completed | March 1, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69a4bb6b075881908e867c25b5080e25 |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:47 p.m.