Triple
T8737131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hacı I Giray |
E207413
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Hacı |
E504955
|
NE 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: Hacı | Statement: [Hacı I Giray, title, Hacı]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hacı Context triple: [Hacı I Giray, title, Hacı]
-
A.
Haji
chosen
Haji is an Islamic honorific title granted to a Muslim who has completed the pilgrimage to Mecca (Hajj).
-
B.
Hacı İlbey
Hacı İlbey was an Ottoman military commander of the 14th century, noted for his key role in the early Ottoman expansion into the Balkans.
-
C.
Al-Haj
Al-Haj is an honorific Islamic title granted to a Muslim who has completed the pilgrimage to Mecca (Hajj).
-
D.
Haji Ali
Haji Ali is a small islet off the coast of Mumbai, India, known for housing the famous Haji Ali Dargah, a revered mosque and tomb visited by pilgrims and tourists alike.
-
E.
Hajji Abdullah
Hajji Abdullah is an alias of Abu Ibrahim al-Hashimi al-Qurashi, the former leader of the Islamic State (ISIS).
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca835a03a081909d4d4cd01a18c9fb |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5d45c96081909aa8509064ff3a04 |
completed | March 31, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf6ef8d7f88190aea21c82da47e4a0 |
completed | April 3, 2026, 7:40 a.m. |
Created at: March 30, 2026, 6:38 p.m.