Triple
T22314947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parthia |
E551617
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Nisa |
—
|
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: Nisa | Statement: [Parthia, capital, Nisa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nisa Context triple: [Parthia, capital, Nisa]
-
A.
Nisa
chosen
Nisa was an ancient city that served as an early royal center of the Parthian Empire, located near present-day Ashgabat in Turkmenistan.
-
B.
Nisa
Nisa is a town that is twinned with Liberec, forming part of an international municipal partnership.
-
C.
An Nisa
An Nisa is the fourth chapter of the Quran, known for its detailed guidance on social justice, family law, and the rights and responsibilities of women and orphans in Islamic society.
-
D.
The Twa Herds
"The Twa Herds" is a satirical poem by Robert Burns that mocks religious hypocrisy and clerical disputes in 18th-century Scotland.
-
E.
Naven
Naven is an anthropological study by Gregory Bateson that analyzes the ritual practices and social structure of the Iatmul people of New Guinea.
- 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_69e11e4776588190abb21e5cea79973f |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1575287688190aa642bb49b24f5a1 |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:42 p.m.