Triple
T1988066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sahih al-Bukhari |
E43185
|
entity |
| Predicate | approximateNumberOfHadithWithoutRepetition |
P26982
|
FINISHED |
| Object | around 2600 |
—
|
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: around 2600 | Statement: [Sahih al-Bukhari, approximateNumberOfHadithWithoutRepetition, around 2600]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateNumberOfHadithWithoutRepetition Context triple: [Sahih al-Bukhari, approximateNumberOfHadithWithoutRepetition, around 2600]
-
A.
hadithNarrationsCountApprox
chosen
Indicates an approximate number of hadith narrations associated with an entity.
-
B.
numberOfPilgrimagesToMecca
Indicates the count of times an entity has undertaken a pilgrimage to Mecca.
-
C.
approximateNumberOfVerses
Indicates an estimated or approximate count of verses associated with an entity.
-
D.
approximateNumberOfTractates
Indicates a relationship where an entity is associated with an estimated or non-exact count of tractates linked to it.
-
E.
hadithsNarrated
Indicates that one entity (typically a person) has narrated, transmitted, or reported the hadiths associated with another entity (such as a collection, text, or individual hadith).
- 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_69a88713ddc88190a969715658ebe7a8 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8ee02dc81908fec9fd8df7a4f40 |
completed | March 7, 2026, 5:34 a.m. |
| PD | Predicate disambiguation | batch_69abb79ad6888190be99943a9c73cf3e |
completed | March 7, 2026, 5:28 a.m. |
Created at: March 4, 2026, 7:37 p.m.