Triple
T9620760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Narmada Bachao Andolan v. Union of India |
E232334
|
entity |
| Predicate | relatedToRight |
P49059
|
FINISHED |
| Object | right to life |
—
|
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: right to life | Statement: [Narmada Bachao Andolan v. Union of India, relatedToRight, right to life]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedToRight Context triple: [Narmada Bachao Andolan v. Union of India, relatedToRight, right to life]
-
A.
relatedTo
Indicates a general, non-specific relationship or association exists between two entities.
-
B.
associatedWithRight
chosen
Indicates a relationship in which an entity is connected to, linked with, or related to something characterized as "right" (such as a right-hand side, a legal right, or a correct option), depending on the domain context.
-
C.
relatedType
Indicates that one entity is connected to another through a specified type or category of relationship.
-
D.
moreCloselyRelatedTo
Indicates that one entity has a stronger or closer relationship, connection, or similarity to a second entity than to some other reference entity.
-
E.
laterRelationWith
Indicates that one entity stands in a temporal relationship to another such that it occurs or exists at a later time than the other.
- 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_69ca84867bb88190b4b57dd5a56d5691 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9ad3a8d88190b1414aa676d82f36 |
completed | April 1, 2026, 10:23 p.m. |
| PD | Predicate disambiguation | batch_69ccd5aa1d2c8190a287bf1cf4a3037e |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:09 p.m.