Triple
T21018311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zarafshan River valley |
E517736
|
entity |
| Predicate | archaeologicalSiteInValley |
P113113
|
FINISHED |
| Object | Afrasiab |
—
|
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: Afrasiab | Statement: [Zarafshan River valley, archaeologicalSiteInValley, Afrasiab]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Afrasiab Context triple: [Zarafshan River valley, archaeologicalSiteInValley, Afrasiab]
-
A.
Afrasiab
Afrasiab is a legendary Turanian king and formidable adversary of Iran in the Persian epic Shahnameh.
-
B.
Tushpa
Tushpa was the ancient fortified city on the eastern shore of Lake Van that served as the political and cultural center of the Kingdom of Urartu in the early first millennium BCE.
-
C.
Sarakhs
Sarakhs is a historic border city in northeastern Iran, known for its strategic location along ancient trade routes between Iran and Central Asia.
-
D.
Panjikent
chosen
Panjikent was an important ancient Sogdian city in present-day Tajikistan, known for its well-preserved wall paintings and role as a Silk Road trading center.
-
E.
Balkh
Balkh is an ancient city in northern Afghanistan, historically a major center of Persian culture, trade, and Islamic scholarship.
- 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.