Triple
T20931189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | White Demon |
E515473
|
entity |
| Predicate | hasAdversary |
P68850
|
FINISHED |
| Object | Rostam |
—
|
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: Rostam | Statement: [White Demon, hasAdversary, Rostam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rostam Context triple: [White Demon, hasAdversary, Rostam]
-
A.
Rostam
Rostam is a city in Iran’s Fars Province, known as a local administrative and population center within the region.
-
B.
Rostam
chosen
Rostam is the legendary Persian hero of the Shahnameh, famed for his superhuman strength, epic battles, and central role in Iran’s mytho-historical epics.
-
C.
Rostam Farrokhzād
Rostam Farrokhzād was a prominent Sasanian military commander and nobleman, best known for leading the Persian forces against the early Muslim armies during the Arab conquest of Iran.
-
D.
Farhad
Farhad is a legendary tragic lover and sculptor in Persian literature, best known for his unrequited love and heroic labors in the romance of Khosrow and Shirin.
-
E.
Dinarzad
Dinarzad is a character in The Arabian Nights, known as Shahrazad’s younger sister who prompts her to tell stories each night to the king.
- 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_69e0b4fb431c8190b9d40e6a72f0cc87 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f6557e4881909ce932c3f538304a |
completed | April 21, 2026, 4 a.m. |
Created at: April 16, 2026, 12:49 p.m.