Triple
T1586687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gwangan Bridge |
E34081
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Centum City |
E157613
|
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: Centum City | Statement: [Gwangan Bridge, connects, Centum City]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Centum City Context triple: [Gwangan Bridge, connects, Centum City]
-
A.
Centum City
chosen
Centum City is a major modern business and entertainment district in Busan, South Korea, known for its high-rise complexes, shopping centers, and cultural venues.
-
B.
Davidville
Davidville was the original company founded by David Karp that created and initially operated the microblogging platform Tumblr.
-
C.
Azalea City
Azalea City is a nickname for Mobile, Alabama, highlighting the city's abundance of blooming azalea flowers and its reputation for vibrant Southern gardens.
-
D.
Limestone City
Limestone City is a nickname for Kingston, Ontario, reflecting its many historic buildings constructed from local limestone.
-
E.
Festival City
Festival City is a popular nickname for Edmonton, Alberta, highlighting its reputation for hosting numerous festivals and cultural events throughout the year.
- 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_69a885fceb2c8190b47e0f7c0aefbff0 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a908f3b5f48190bd5eff3ce81c5ffb |
completed | March 5, 2026, 4:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad4037bbdc81909bcf9c5c7a7f5de5 |
completed | March 8, 2026, 9:24 a.m. |
Created at: March 4, 2026, 7:27 p.m.