Triple
T5737194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dharma |
E126529
|
entity |
| Predicate | roleInEthics |
P9237
|
FINISHED |
| Object | guides right action |
—
|
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: guides right action | Statement: [Dharma, roleInEthics, guides right action]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInEthics Context triple: [Dharma, roleInEthics, guides right action]
-
A.
positionOnEthics
Indicates a stance, viewpoint, or opinion that an entity holds regarding ethical principles, issues, or practices.
-
B.
hasEthicalRole
chosen
Indicates that an entity holds a position, function, or responsibility defined in terms of ethical duties, norms, or moral obligations in relation to another entity or context.
-
C.
ethicalResponsibility
Indicates a relationship in which an entity is morally obligated to act, decide, or respond in a certain way toward another entity or situation.
-
D.
roleInAddressing
Indicates the specific function or responsibility an entity has in dealing with or responding to a particular issue, situation, or task.
-
E.
typeOfEthicsLaw
Indicates that a given law pertains specifically to a particular category or type within the broader domain of ethics-related legislation.
- 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_69c0083082288190b7478cead6b5430a |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0255ad6f48190977bf4f037110aa3 |
completed | March 22, 2026, 5:22 p.m. |
| PD | Predicate disambiguation | batch_69c021c8195481909419808b002628aa |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:47 p.m.