Triple
T21017895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Afrasiab |
E517727
|
entity |
| Predicate | fatherOf |
P120
|
FINISHED |
| Object | Farangis |
—
|
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: Farangis | Statement: [Afrasiab, fatherOf, Farangis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Farangis Context triple: [Afrasiab, fatherOf, Farangis]
-
A.
Farangis
chosen
Farangis is a noblewoman in the Persian epic Shahnameh, best known as the wife of the tragic hero Siyavash and the mother of the legendary prince Kay Khosrow.
-
B.
Gurandukht
Gurandukht was a medieval Georgian noblewoman and queen consort, known primarily as the wife of King David IV "the Builder" of Georgia.
-
C.
Gurandukht
Gurandukht was a medieval Cuman princess known from Georgian and regional Caucasian historical sources, often mentioned in the context of dynastic and political alliances.
-
D.
Roxanna
Roxanna is a feminine given name of Persian origin, commonly interpreted to mean "dawn" or "bright."
-
E.
Fedalma
Fedalma is a notable painting by American artist George Fuller, recognized for its evocative, romantic style and atmospheric portrayal of its female subject.
- 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_69e0b50262b081909bc488937145eb73 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc5a27f08190b26828a6a7b59f7c |
completed | April 21, 2026, 4:26 a.m. |
Created at: April 16, 2026, 1:54 p.m.