Triple
T3776859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Disaster Movie |
E83328
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Aaron Seltzer |
E387334
|
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: Aaron Seltzer | Statement: [Disaster Movie, writer, Aaron Seltzer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aaron Seltzer Context triple: [Disaster Movie, writer, Aaron Seltzer]
-
A.
Aaron Seltzer
chosen
Aaron Seltzer is an American filmmaker best known for co-writing and co-directing a series of parody films such as "Date Movie," "Epic Movie," and "Meet the Spartans."
-
B.
Paul Lieberstein
Paul Lieberstein is an American writer, producer, and actor best known for playing HR representative Toby Flenderson and serving as a key writer and showrunner on the U.S. version of "The Office."
-
C.
Evan Goldberg
Evan Goldberg is a technology entrepreneur best known for founding the cloud-based business software company NetSuite.
-
D.
Rob Corddry
Rob Corddry is an American actor and comedian best known for his work on "The Daily Show" and in films like "Hot Tub Time Machine."
-
E.
Albert Brooks
Albert Brooks is an American actor, comedian, writer, and director known for his neurotic, satirical humor and films such as "Defending Your Life" and "Lost in America."
- 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_69ad8b235e608190b5a2b1d1bfcef50b |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc5be3c48190a72e840d8214bb74 |
completed | March 8, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4f03d3df48190a4b2382059b7bb24 |
completed | March 14, 2026, 5:21 a.m. |
Created at: March 8, 2026, 3:36 p.m.