Triple
T10365042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Storage Wars |
E244229
|
entity |
| Predicate | narratedBy |
P2181
|
FINISHED |
| Object | Thom Beers |
E708295
|
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: Thom Beers | Statement: [Storage Wars, narratedBy, Thom Beers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thom Beers Context triple: [Storage Wars, narratedBy, Thom Beers]
-
A.
Thom Beers
chosen
Thom Beers is an American television producer and narrator best known for creating and producing gritty, reality-based series such as "Deadliest Catch" and other shows focused on dangerous occupations and extreme situations.
-
B.
Mike Beedle
Mike Beedle was a software engineer, author, and early proponent of agile and Scrum methodologies who helped popularize agile software development practices worldwide.
-
C.
Ben Straub
Ben Straub is a software developer and technical author best known for co-authoring the widely used Git reference book "Pro Git."
-
D.
Harry Bradbeer
Harry Bradbeer is a British television and film director best known for his work on acclaimed series like "Fleabag" and the mystery film "Enola Holmes."
-
E.
Andy Fickman
Andy Fickman is an American film and television director known for family-friendly comedies and energetic, commercially successful studio movies.
- 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e964a53c8190b748e80850e96656 |
completed | April 7, 2026, 11:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d89f53484881909fb976efb3882b9b |
completed | April 10, 2026, 6:57 a.m. |
Created at: April 6, 2026, noon