Triple
T10669527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dongdan |
E251449
|
entity |
| Predicate | hasRoad |
P959
|
FINISHED |
| Object | Dongdan North Street |
E251449
|
NE FINISHED |
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: Dongdan North Street | Statement: [Dongdan, hasRoad, Dongdan North Street]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dongdan North Street Context triple: [Dongdan, hasRoad, Dongdan North Street]
-
A.
Sifang Street
Sifang Street is the central square and bustling commercial and social hub of Lijiang’s Old Town, known for its traditional Naxi architecture, shops, and lively atmosphere.
-
B.
Damuqiao Road
Damuqiao Road is a Shanghai Metro station and major transit point located in the central area of Shanghai, China.
-
C.
Dong’an Road
Dong’an Road is a station on the Shanghai Metro system, serving passengers in the city’s central area.
-
D.
Dongdan
chosen
Dongdan is a central commercial and transportation hub in Beijing known for its shopping streets, offices, and busy intersections.
-
E.
Caoyang Road
Caoyang Road is a Shanghai Metro interchange station serving multiple lines in the Putuo District of Shanghai, China.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6aa5b0d2881909584b20efc5877f0 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6f861513881909b44c711371086b7 |
completed | April 9, 2026, 12:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d98865f700819093c8cadc6fcef75f |
completed | April 10, 2026, 11:31 p.m. |
Created at: April 8, 2026, 9:09 p.m.