Triple
T21480203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Star Wars Holiday Special |
E529966
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Pat Proft |
—
|
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: Pat Proft | Statement: [The Star Wars Holiday Special, writer, Pat Proft]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pat Proft Context triple: [The Star Wars Holiday Special, writer, Pat Proft]
-
A.
Pat Proft
chosen
Pat Proft is an American comedy writer and screenwriter best known for his work on spoof film franchises such as The Naked Gun and Police Academy.
-
B.
Alan Emtage
Alan Emtage is a computer scientist best known for creating Archie, the first widely used Internet search engine, which laid foundational groundwork for modern web search.
-
C.
Guy McAfee
Guy McAfee was a former Los Angeles police officer turned influential Las Vegas casino owner and gambling figure who helped shape the city’s early Strip-era development.
-
D.
Rob Williams
Rob Williams is a British comic book writer best known for his work on major titles for publishers like DC and Marvel, including a prominent run on Suicide Squad.
-
E.
Chris Meyer
Chris Meyer is an actor known for his role in the film "Treachery."
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea1b0130819088b8e96ddbb29317 |
completed | April 23, 2026, 9:44 a.m. |
Created at: April 16, 2026, 6:20 p.m.