Triple
T13602966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fracture |
E324988
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | David Rosenbloom |
E389035
|
NE FINISHED |
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: David Rosenbloom | Statement: [Fracture, editedBy, David Rosenbloom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Rosenbloom Context triple: [Fracture, editedBy, David Rosenbloom]
-
A.
David Rosenbloom
chosen
David Rosenbloom is a film editor known for his work on major Hollywood productions, including the science fiction movie "Transcendence."
-
B.
Steven Rosenblum
Steven Rosenblum is a film editor best known for his frequent collaborations with director Edward Zwick on movies such as "Blood Diamond," "Glory," and "The Last Samurai."
-
C.
Daniel Blumberg
Daniel Blumberg is a British musician and composer known for his experimental work in indie rock and film scores.
-
D.
Dave Rosenberg
Dave Rosenberg is a technology entrepreneur best known as a co-founder of MuleSoft, a leading integration and API management platform company.
-
E.
Michael Jaffe
Michael Jaffe is an American television and film producer known for his work on numerous TV movies, series, and feature films.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d80769eaf081909d82f44e484d6113 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb07ca07481909c45da551ea61ab4 |
completed | April 12, 2026, 2:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffcf0513f88190b2405ffc32f1e9c7 |
completed | May 10, 2026, 12:19 a.m. |
Created at: April 9, 2026, 9:49 p.m.