Triple
T20702691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Due South |
E508821
|
entity |
| Predicate | hasMainCharacter |
P1183
|
FINISHED |
| Object | Ray Kowalski |
—
|
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: Ray Kowalski | Statement: [Due South, hasMainCharacter, Ray Kowalski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ray Kowalski Context triple: [Due South, hasMainCharacter, Ray Kowalski]
-
A.
Ray Kowalski
chosen
Ray Kowalski is a fictional Chicago detective who becomes Constable Benton Fraser’s streetwise and impulsive partner in the Canadian television series "Due South."
-
B.
Walt Kowalski
Walt Kowalski is a gruff, widowed Korean War veteran whose evolving relationship with his Hmong neighbors drives the emotional and moral core of the film "Gran Torino."
-
C.
Dave Kovic
Dave Kovic is the affable presidential look-alike who impersonates the U.S. President in the political comedy film "Dave."
-
D.
Melvin Frohike
Melvin Frohike is a conspiracy-obsessed, tech-savvy hacker and member of the Lone Gunmen trio from The X-Files universe.
-
E.
Jacob Kowalski
Jacob Kowalski is a kind-hearted No-Maj baker who becomes a close friend and ally to Newt Scamander in the Fantastic Beasts film series.
- 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_69e0b4c2b2a481909e31e9cb8f81ab55 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c18cb9cc819095d0669dca037424 |
completed | April 21, 2026, 12:15 a.m. |
Created at: April 16, 2026, 12:13 p.m.