Triple
T34797995
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daedric Princes |
E1003139
|
entity |
| Predicate | typicalMoralView |
P55782
|
FINISHED |
| Object | morally ambiguous |
—
|
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: morally ambiguous | Statement: [Daedric Princes, typicalMoralView, morally ambiguous]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalMoralView Context triple: [Daedric Princes, typicalMoralView, morally ambiguous]
-
A.
moralBelief
Indicates that an agent holds a normative judgment about what is right, wrong, good, or bad in a given context.
-
B.
moralAttitude
chosen
Indicates a subject’s evaluative stance or judgment about the moral rightness or wrongness of another entity, action, or situation.
-
C.
moralTendency
Indicates a general inclination or propensity of an entity to act in ways judged as morally right or wrong.
-
D.
moralConcept
Indicates that one entity represents or embodies a moral or ethical concept in relation to another.
-
E.
moralAssumption
Indicates that one entity presumes or accepts a moral principle, value, or norm as valid or binding in a given context.
- 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_69f76db543808190b188c6c86a91491b |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379fd7aac8190873077e63873aa72 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 3:59 p.m.