Triple
T17719852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duluth Aerial Lift Bridge |
E442302
|
entity |
| Predicate | engineer |
P184
|
FINISHED |
| Object | C.A.P. Turner |
—
|
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: C.A.P. Turner | Statement: [Duluth Aerial Lift Bridge, engineer, C.A.P. Turner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: C.A.P. Turner Context triple: [Duluth Aerial Lift Bridge, engineer, C.A.P. Turner]
-
A.
C.A.P. Turner
chosen
C.A.P. Turner was an American civil engineer and pioneering bridge designer known for innovative structural systems in the early 20th century.
-
B.
Al Capps
Al Capps was an American arranger, composer, and producer known for his work on numerous pop recordings in the 1960s and 1970s, including co-writing the hit song "Half-Breed."
-
C.
Peter Turner
Peter Turner is a British actor and writer best known for his memoir about his relationship with Gloria Grahame, which was adapted into the film "Film Stars Don’t Die in Liverpool."
-
D.
Ed Turner
Ed Turner is an American astrophysicist known for his work in cosmology and gravitational lensing, and for his long association with Princeton University.
-
E.
Carl Turney
Carl Turney is a healthcare professional associated with a medical clinic.
- 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_69d8b9ec79688190b86bdcef85a7b3aa |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e474844ff48190b1cf181eb9c113d9 |
completed | April 19, 2026, 6:21 a.m. |
Created at: April 10, 2026, 10:07 a.m.