Triple
T18853927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kayqubad II |
E461120
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Gürcü Hatun |
—
|
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: Gürcü Hatun | Statement: [Kayqubad II, mother, Gürcü Hatun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gürcü Hatun Context triple: [Kayqubad II, mother, Gürcü Hatun]
-
A.
Gürcü Hatun
chosen
Gürcü Hatun was a 13th-century Georgian princess who became a prominent Seljuk queen consort through her marriage to Sultan Kaykhusraw II.
-
B.
Dürrinev Kadın
Dürrinev Kadın was a consort of Ottoman Sultan Abdülaziz and held the title of BaşKadin (chief consort) in the 19th-century Ottoman imperial harem.
-
C.
Ketevan
Ketevan is a Georgian female given name, often associated with historical and cultural figures from Georgia.
-
D.
Asporça Hatun
Asporça Hatun was a consort of the early Ottoman ruler Orhan Gazi and a notable figure in the formative period of the Ottoman dynasty.
-
E.
Güls
Güls is a district of the German city of Koblenz, situated along the Moselle River and known for its winegrowing and scenic riverside setting.
- 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_69d8dcfa11e4819090ab1ef5bdcd2b2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c05b4d8881909af0238f451b0e31 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 10, 2026, 11:56 a.m.