Triple
T19880019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragonfly (2002 film) |
E477744
|
entity |
| Predicate | storyBy |
P1955
|
FINISHED |
| Object | Mike Thompson |
—
|
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: Mike Thompson | Statement: [Dragonfly (2002 film), storyBy, Mike Thompson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mike Thompson Context triple: [Dragonfly (2002 film), storyBy, Mike Thompson]
-
A.
Mike Thompson
chosen
Mike Thompson is a screenwriter best known for his work on the romantic comedy film "Nine Months."
-
B.
John Garamendi
John Garamendi is an American politician and public official who has served in roles including California insurance commissioner and U.S. Representative.
-
C.
Chris Cox
Chris Cox is an American DJ, remixer, and producer best known as one half of the influential dance music remix duo Thunderpuss.
-
D.
Jared Huffman
Jared Huffman is a Democratic U.S. Representative from California known for his work on environmental protection, public lands, and progressive policy issues.
-
E.
Tom Bray
Tom Bray is a film editor known for his work on the action-horror movie "Drive Angry."
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658de4b288190a41bee67f570be1e |
completed | April 20, 2026, 4:48 p.m. |
Created at: April 10, 2026, 1:52 p.m.