Triple
T20188635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Falling Down |
E492926
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Timothy Harris |
—
|
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: Timothy Harris | Statement: [Falling Down, producer, Timothy Harris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Timothy Harris Context triple: [Falling Down, producer, Timothy Harris]
-
A.
Timothy Harris
chosen
Timothy Harris is an American screenwriter and producer known for co-writing popular comedies such as "Brewster's Millions," "Trading Places," and "Twins."
-
B.
William Harris
William Harris was a historical English church musician who served in the prestigious role of Master of the Children, overseeing and training choristers.
-
C.
Benjamin Hammond Haggerty
Benjamin Hammond Haggerty is an American rapper and songwriter best known by his stage name Macklemore, recognized for hits like "Thrift Shop" and "Can't Hold Us."
-
D.
Josef A. Harris
Josef A. Harris is known primarily as the husband of historian and author Mary Nash.
-
E.
James B. Harris
James B. Harris is an American film producer and director best known for his collaborations with Stanley Kubrick on several influential mid-20th-century films.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66ad404508190981cfb7cab18d8d3 |
completed | April 20, 2026, 6:05 p.m. |
Created at: April 11, 2026, 11:37 p.m.