Triple
T18589647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harper (film) |
E454327
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Stefan Arnsten |
—
|
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: Stefan Arnsten | Statement: [Harper (film), editedBy, Stefan Arnsten]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stefan Arnsten Context triple: [Harper (film), editedBy, Stefan Arnsten]
-
A.
Stefan Arnsten
chosen
Stefan Arnsten is a film editor best known for his work on the 1971 cult road movie "Vanishing Point."
-
B.
Olaf Sporns
Olaf Sporns is a neuroscientist known for his pioneering work in network neuroscience and the study of brain connectivity.
-
C.
Steven Chasman
Steven Chasman is a film producer best known for his work on action and crime movies, frequently collaborating with stars like Jason Statham.
-
D.
Erik J. Sorensen
Erik J. Sorensen is an American organic chemist known for his work in complex molecule synthesis and as a professor at Princeton University.
-
E.
Erik D. Herzog
Erik D. Herzog is an American neuroscientist and chronobiologist known for his research on the neural and molecular mechanisms underlying circadian rhythms.
- 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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e545b4a2a0819098047ee81278bd9d |
completed | April 19, 2026, 9:14 p.m. |
Created at: April 10, 2026, 11:44 a.m.