Triple
T19579540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ken Scott |
E489949
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Delivery Man |
—
|
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: Delivery Man | Statement: [Ken Scott, directed, Delivery Man]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Delivery Man Context triple: [Ken Scott, directed, Delivery Man]
-
A.
Delivery Man
chosen
Delivery Man is a 2013 comedy-drama film starring Vince Vaughn as a man who discovers he has fathered hundreds of children through anonymous sperm donations.
-
B.
Courier
Courier is a 1986 Soviet coming-of-age drama film directed by Karen Shakhnazarov that explores youth, class, and disillusionment in the late Soviet era.
-
C.
Delivery Hero
Delivery Hero is a global online food delivery and quick-commerce company that operates numerous delivery platforms and brands across multiple countries.
-
D.
McDelivery
McDelivery is McDonald’s food delivery service that allows customers to order menu items for home or office delivery via apps, websites, or partner platforms.
-
E.
GrabExpress
GrabExpress is Grab’s on-demand parcel and document delivery service operating across various Southeast Asian cities.
- 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_69d8e8dd9374819098e36349b3211663 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6402763b8819099e535979f094f9d |
completed | April 20, 2026, 3:03 p.m. |
Created at: April 10, 2026, 1:42 p.m.