Triple
T21574310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haft Awrang |
E532358
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Subhat al-Abrar |
—
|
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: Subhat al-Abrar | Statement: [Haft Awrang, hasPart, Subhat al-Abrar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Subhat al-Abrar Context triple: [Haft Awrang, hasPart, Subhat al-Abrar]
-
A.
Subhat al-Abrār
chosen
Subhat al-Abrār is a celebrated Persian poetic work by the 15th-century poet Jami, known for its didactic and mystical themes within the Islamic literary tradition.
-
B.
Rawzat al-anwār
Rawzat al-anwār is a celebrated Persian mystical and romantic masnavi by the 14th-century poet Khwaju Kermani.
-
C.
Safinat-ul-Auliya
Safinat-ul-Auliya is a Persian hagiographical work by Mughal prince Dara Shikoh that compiles biographies and spiritual teachings of prominent Sufi saints.
-
D.
Al-Asma ul-Husna
Al-Asma ul-Husna refers to the 99 beautiful and perfect names of Allah in Islamic theology, each expressing a distinct divine attribute.
-
E.
Khudā-e Sukhan
Khudā-e Sukhan is an honorific title meaning "God of Poetry," traditionally bestowed upon the renowned Urdu poet Mir Taqi Mir for his unmatched mastery of the art.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c4618bec8190bcb0feb74568cbb1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eee9cef2748190990a81967d49b706 |
completed | April 27, 2026, 4:45 a.m. |
Created at: April 16, 2026, 6:30 p.m.