Triple
T15312517
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghai Knights |
E366071
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Roy O'Bannon |
E1154501
|
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: Roy O'Bannon | Statement: [Shanghai Knights, mainCharacter, Roy O'Bannon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roy O'Bannon Context triple: [Shanghai Knights, mainCharacter, Roy O'Bannon]
-
A.
Roy O'Bannon
chosen
Roy O'Bannon is a charming but inept outlaw and comic sidekick portrayed by Owen Wilson in the action-comedy Western film "Shanghai Noon."
-
B.
Vernan Keenan
Vernan Keenan was an American roller coaster designer best known for creating the iconic Cyclone wooden coaster at Coney Island.
-
C.
Glen Tullman
Glen Tullman is an American healthcare technology entrepreneur and executive best known for leading and building major digital health companies, including Allscripts.
-
D.
Sam Burrows
Sam Burrows is best known as the husband of English singer-songwriter and podcaster Jessie Ware.
-
E.
Don Burgess
Don Burgess is an American cinematographer best known for his Oscar-nominated work on the film "Forrest Gump" and his frequent collaborations with director Robert Zemeckis.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03cd2d5a88190aead748920f93d47 |
completed | April 16, 2026, 1:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff1a6582908190a9a56652e9ccc5a1 |
completed | May 9, 2026, 11:28 a.m. |
Created at: April 10, 2026, 3:16 a.m.