Triple
T17441797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bursa Grand Bazaar |
E424672
|
entity |
| Predicate | nearby |
P350
|
FINISHED |
| Object | Koza Han |
—
|
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: Koza Han | Statement: [Bursa Grand Bazaar, nearby, Koza Han]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Koza Han Context triple: [Bursa Grand Bazaar, nearby, Koza Han]
-
A.
Koza Han
chosen
Koza Han is a historic Ottoman-era silk market and caravanserai in Bursa, Turkey, renowned as a center of the city’s centuries-old silk trade.
-
B.
Shōji-ko
Shōji-ko is one of the Fuji Five Lakes in Yamanashi Prefecture, Japan, known for its scenic views of Mount Fuji and relatively undeveloped, tranquil surroundings.
-
C.
Yokoze
Yokoze is a small town in Saitama Prefecture, Japan, known for its rural scenery and proximity to the Chichibu mountain area.
-
D.
Kazegaura
Kazegaura is a tranquil, wind-swept lakeside town in the visual novel "If My Heart Had Wings," known for its scenic vistas and serene atmosphere.
-
E.
Fukusaki
Fukusaki is a town in Hyōgo Prefecture, Japan, known for its rural setting and association with folklorist Kunio Yanagita.
- 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e44ff82bbc819095dd0621137da809 |
completed | April 19, 2026, 3:46 a.m. |
Created at: April 10, 2026, 5:46 a.m.