Triple
T22495981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Finch |
E556141
|
entity |
| Predicate | createdBy |
P806
|
FINISHED |
| Object | Adam Herz |
—
|
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: Adam Herz | Statement: [Finch, createdBy, Adam Herz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adam Herz Context triple: [Finch, createdBy, Adam Herz]
-
A.
Adam Herz
chosen
Adam Herz is an American screenwriter best known for creating and writing the hit teen comedy film "American Pie" and its sequels.
-
B.
Adam Aaronson
Adam Aaronson is a member of the musical group High Speed Scene, known for its energetic rock sound.
-
C.
Adam Gerstel
Adam Gerstel is a film editor known for his work on major Hollywood productions, including Marvel Studios projects.
-
D.
Jonathan Zalben
Jonathan Zalben is a film and television composer known for scoring a variety of independent features and documentaries.
-
E.
Uriel Frisch
Uriel Frisch is a French physicist and mathematician renowned for his contributions to fluid dynamics and turbulence theory.
- 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_69e11e5445bc8190b6a9481926db3355 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15cb2644c819094864bd88bcebcbd |
completed | April 29, 2026, 1:19 a.m. |
Created at: April 16, 2026, 8:49 p.m.