Triple
T26757378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prophet Moses in Islam |
E674709
|
entity |
| Predicate | preachedReligion |
P44623
|
FINISHED |
| Object | Tawhid (oneness of God) |
—
|
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: Tawhid (oneness of God) | Statement: [Prophet Moses in Islam, preachedReligion, Tawhid (oneness of God)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preachedReligion Context triple: [Prophet Moses in Islam, preachedReligion, Tawhid (oneness of God)]
-
A.
preached
chosen
Indicates that one entity delivered a religious or moral message or sermon to others.
-
B.
preachesFrom
Indicates that a person delivers a sermon, teaching, or religious message using a particular text, source, or location as the basis.
-
C.
promotedReligion
Indicates that an entity actively supported, advocated for, or worked to spread a particular religion.
-
D.
religiousTransmission
Indicates the passing on or spread of religious beliefs, practices, or traditions from one entity to another.
-
E.
religiousEnvironment
Indicates the religious context, atmosphere, or setting in which an entity exists or an action takes place.
- 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_69eecda6e9dc81908452fab3ba17ed9b |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f618d6dad48190b2bcb3ddf080dadf |
completed | May 2, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 3:56 a.m.