Triple
T902657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saraswati |
E19478
|
entity |
| Predicate | originalAspect |
P20183
|
FINISHED |
| Object | river goddess |
—
|
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: river goddess | Statement: [Saraswati, originalAspect, river goddess]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalAspect Context triple: [Saraswati, originalAspect, river goddess]
-
A.
originalType
Indicates that one entity represents the initial or source type from which another entity is derived, transformed, or reclassified.
-
B.
originallyIn
Indicates that something first appeared, was created, or was initially located within a particular context, source, or place.
-
C.
aspect
Indicates a specific temporal phase or manner in which an action, event, or state unfolds or is viewed (e.g., ongoing, completed, habitual).
-
D.
originalHolder
Indicates that an entity is the initial possessor or owner of another entity before any transfer, change, or reassignment occurs.
-
E.
originalText
Indicates that one text is the initial, unmodified version from which other versions, translations, or representations are derived.
- F. None of above. chosen
Provenance (4 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_69a4939e889c8190ac148b3ac1a7f90b |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ad56f4c08190a7a5091ff0eb3209 |
completed | March 1, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69a4aa98caec8190bbcc38320090f058 |
completed | March 1, 2026, 9:07 p.m. |
| PDg | Predicate description generation | batch_69a4ab60fea8819098ce3269181897d1 |
completed | March 1, 2026, 9:10 p.m. |
Created at: March 1, 2026, 7:39 p.m.