Triple
T9065507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Melek Taus |
E217233
|
entity |
| Predicate | moralStatusInYazidism |
P22659
|
FINISHED |
| Object | entirely good |
—
|
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: entirely good | Statement: [Melek Taus, moralStatusInYazidism, entirely good]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: moralStatusInYazidism Context triple: [Melek Taus, moralStatusInYazidism, entirely good]
-
A.
moralStatus
chosen
Indicates the ethical standing or degree of moral consideration that one entity has in relation to another.
-
B.
statusInIslamicTradition
Indicates the recognized standing, role, or level of esteem an entity holds within Islamic religious, cultural, or scholarly tradition.
-
C.
judgmentCharacterizationInIslamicSources
Indicates how a person, action, or event is evaluated or characterized in Islamic religious or legal sources.
-
D.
normativeStatusInIslam
Indicates the evaluative ruling or status that Islamic law or ethics assigns to an action, practice, or state (e.g., obligatory, recommended, permissible, disliked, or forbidden).
-
E.
moralOutcome
Indicates the moral or ethical status resulting from an action, event, or decision, such as whether it is judged right, wrong, good, or bad.
- 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_69ca83d5a7f48190b16c1e59bd43ede0 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc94bc91d48190acf62afa90eec079 |
completed | April 1, 2026, 3:45 a.m. |
| PD | Predicate disambiguation | batch_69cc65f881248190bfd220bb28a9fb5f |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:11 p.m.