Triple
T33946630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Hour (as-sāʿah) |
E870308
|
entity |
| Predicate | knownOnlyTo |
P142820
|
FINISHED |
| Object | Allah |
—
|
NE NERFINISHED |
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: Allah | Statement: [the Hour (as-sāʿah), knownOnlyTo, Allah]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: knownOnlyTo Context triple: [the Hour (as-sāʿah), knownOnlyTo, Allah]
-
A.
knownOnlyBy
chosen
Indicates that a piece of information or fact is exclusively known by a specific entity and by no others.
-
B.
knownOnlyThrough
Indicates that one entity is aware of or has information about another entity exclusively via a specific intermediary source or channel, and not through any direct or alternative means.
-
C.
recognizedOnlyBy
Indicates that something is acknowledged, identified, or accepted exclusively by a specific entity or group and by no others.
-
D.
knownOnlyToAudienceAs
Indicates that certain information about an entity is available to and recognized by the audience but not known or accessible to other entities within the context.
-
E.
reachableOnlyBy
Indicates that one entity can be accessed or arrived at exclusively through another specific entity or route, with no alternative paths available.
- 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_69f3499b0dd48190b07b4b60babcee02 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f74062b9388190b30546cf700a825c |
completed | May 3, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69f73c802b848190b61a416b7488bd96 |
completed | May 3, 2026, 12:16 p.m. |
Created at: May 1, 2026, 1:49 a.m.