Triple
T3586709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Surah Al-Falaq |
E75926
|
entity |
| Predicate | verse4Focus |
P49511
|
FINISHED |
| Object | evil of sorcerers who blow on knots |
—
|
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: evil of sorcerers who blow on knots | Statement: [Surah Al-Falaq, verse4Focus, evil of sorcerers who blow on knots]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: verse4Focus Context triple: [Surah Al-Falaq, verse4Focus, evil of sorcerers who blow on knots]
-
A.
scriptureFocus
Indicates that something centers on, emphasizes, or is primarily concerned with religious scripture or sacred texts.
-
B.
keyVerse
Indicates that one verse is designated as the central or most thematically important verse in relation to a text, passage, or concept.
-
C.
verse3
Indicates a relationship where one entity is the third verse or stanza associated with another entity, such as a song, poem, or scripture passage.
-
D.
verses
Indicates a relationship where one entity competes or is pitted against another, as in an opposition, matchup, or comparison.
-
E.
memorizationPractice
Indicates engaging in activities or exercises specifically intended to commit information to memory or strengthen recall.
- F. None of above. chosen
Provenance (4 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_69ad85d6dc3c8190b491b79b83e25461 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc137eb708190809cd52b6deb227c |
completed | March 8, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69adb839b4e08190b1c0d611cccb11ae |
completed | March 8, 2026, 5:56 p.m. |
| PDg | Predicate description generation | batch_69adb902e61c81908f10494f828e260f |
completed | March 8, 2026, 5:59 p.m. |
Created at: March 8, 2026, 3:22 p.m.