Triple
T12569957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saw 3D |
E295573
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Mark Hoffman |
E387779
|
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: Mark Hoffman | Statement: [Saw 3D, mainCharacter, Mark Hoffman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Hoffman Context triple: [Saw 3D, mainCharacter, Mark Hoffman]
-
A.
Mark Hoffman
chosen
Mark Hoffman is a fictional serial killer and primary antagonist in the "Saw" horror film franchise, known for continuing Jigsaw’s deadly games.
-
B.
Mark Hoffman
Mark Hoffman is an American technology executive best known as a co-founder and early leader of the database software company Sybase.
-
C.
Gary Hoffman
Gary Hoffman is an acclaimed American cellist renowned for his rich tone, expressive interpretations, and international solo and chamber music performances.
-
D.
David Hoffman
David Hoffman is a common personal name shared by multiple notable individuals across fields such as law, politics, academia, and the arts.
-
E.
Don Harvey
Don Harvey is an American character actor known for his intense supporting roles in films such as the Vietnam War drama "Casualties of War."
- 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_69d6ad9cac2c81908e8a7bed82d1e21d |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d954a422c88190a22cc34d2eac00ce |
completed | April 10, 2026, 7:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f67c6c21348190b851fce31df307e2 |
completed | May 2, 2026, 10:36 p.m. |
Created at: April 8, 2026, 11:50 p.m.