Triple
T14251154
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MacArthur Bridge (Taipei) |
E353264
|
entity |
| Predicate | hasNameForm |
P19207
|
FINISHED |
| Object | 麥帥公路橋 |
E1090430
|
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: 麥帥公路橋 | Statement: [MacArthur Bridge (Taipei), hasNameForm, 麥帥公路橋]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 麥帥公路橋 Context triple: [MacArthur Bridge (Taipei), hasNameForm, 麥帥公路橋]
-
A.
麥帥橋
chosen
麥帥橋是位於臺北市基隆河上的重要跨河橋樑，連接內湖與松山一帶並作為市區主要交通幹道之一。
-
B.
民權橋
民權橋 is a bridge in Taiwan known for carrying Minquan Road across the Keelung River and serving as an important traffic link in Taipei.
-
C.
復興橋
復興橋 is a bridge in Taipei, Taiwan, commonly known as Fuxing Bridge, that serves as an important local traffic connection.
-
D.
Howard Frankland Bridge
The Howard Frankland Bridge is a major highway span across Tampa Bay that serves as a key transportation link between Tampa and St. Petersburg, Florida.
-
E.
Republic Bridge
Republic Bridge is a prominent bridge in central Baghdad, Iraq, spanning the Tigris River and connecting key districts of the city.
- 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_69d8278c43e08190824146f4632b89a5 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6296f9d0819086f62f525d07eb12 |
completed | April 14, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd3d127f0c81908dea42ca09c1abda |
completed | May 8, 2026, 1:32 a.m. |
Created at: April 10, 2026, 1:08 a.m.