Triple
T18737681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savitrī |
E458206
|
entity |
| Predicate | responseToProphecy |
P67059
|
FINISHED |
| Object | chooses to marry Satyavān despite knowing his fate |
—
|
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: chooses to marry Satyavān despite knowing his fate | Statement: [Savitrī, responseToProphecy, chooses to marry Satyavān despite knowing his fate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: responseToProphecy Context triple: [Savitrī, responseToProphecy, chooses to marry Satyavān despite knowing his fate]
-
A.
givesProphecy
Indicates that one entity delivers or reveals a prophecy to another entity.
-
B.
containsProphecyAbout
Indicates that one entity includes or conveys a prediction or foretelling specifically concerning another entity.
-
C.
relatedProphecy
Indicates that there exists a prophetic connection or foretelling relationship between the entities involved.
-
D.
basedOnProphecyBy
Indicates that something occurs, is created, or is decided as a result of guidance, information, or prediction given by a particular prophecy or prophet.
-
E.
reactionToProphecy
chosen
Indicates how an entity responds or behaves in consequence to a given prophecy.
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5768b80ac8190bc05628d64f86fc9 |
completed | April 20, 2026, 12:42 a.m. |
| PD | Predicate disambiguation | batch_69e48d03766c8190a43f7681842f4f8d |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:51 a.m.