Triple
T4090533
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sammo Hung |
E87691
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Pedicab Driver |
E413060
|
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: Pedicab Driver | Statement: [Sammo Hung, directed, Pedicab Driver]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pedicab Driver Context triple: [Sammo Hung, directed, Pedicab Driver]
-
A.
Pedicab Driver
chosen
Pedicab Driver is a 1989 Hong Kong action-comedy film directed by and starring Sammo Hung, known for its blend of martial arts, drama, and character-driven storytelling set around pedicab workers in Macau.
-
B.
Uber
Uber is a global ride-hailing and technology company that connects passengers with drivers through a mobile app and has expanded into food delivery and freight services.
-
C.
Tipper
Tipper is the commonly used nickname of Mary Elizabeth Gore, an American social issues advocate and the wife of former U.S. Vice President Al Gore.
-
D.
Meru Cabs
Meru Cabs is an Indian radio taxi and ride-hailing company that was one of the country’s early organized cab service providers.
-
E.
Uber Pro
Uber Pro is a rewards and loyalty program that provides benefits and incentives to Uber drivers based on their performance and activity.
- 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_69aed94425148190be337845d56fac22 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefcab0a1c8190a1b0ca48ebc95b31 |
completed | March 9, 2026, 5 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5769e8b188190a6356c325d0551ea |
completed | March 14, 2026, 2:54 p.m. |
Created at: March 9, 2026, 3:39 p.m.