Triple
T4782105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaikeyi |
E106389
|
entity |
| Predicate | laterFelt |
P6381
|
FINISHED |
| Object | remorse for sending Rama to exile |
—
|
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: remorse for sending Rama to exile | Statement: [Kaikeyi, laterFelt, remorse for sending Rama to exile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterFelt Context triple: [Kaikeyi, laterFelt, remorse for sending Rama to exile]
-
A.
feltIn
Indicates that a sensation, emotion, or effect is experienced within a particular location, context, or entity.
-
B.
laterPerception
chosen
Indicates that one entity’s perception, awareness, or observation of something occurs after another specified time, event, or perception.
-
C.
laterSought
Indicates that one entity attempted to obtain, pursue, or request another entity at a subsequent time relative to some prior reference point.
-
D.
laterRaised
Indicates that one entity was raised, elevated, or brought up at a time subsequent to another referenced event or state.
-
E.
feels
Indicates that an entity experiences or has a particular emotion, sensation, or internal state in relation to something.
- 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_69bd43f4a9588190bf73e20bc27c03cc |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd69237f80819090713ed62653fb75 |
completed | March 20, 2026, 3:34 p.m. |
| PD | Predicate disambiguation | batch_69bd622be1388190ab5511b589c878c0 |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:22 p.m.