Triple
T12574288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Cursed Earth |
E300165
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | John Wagner |
E300155
|
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: John Wagner | Statement: [The Cursed Earth, writer, John Wagner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Wagner Context triple: [The Cursed Earth, writer, John Wagner]
-
A.
John Wagner
John Wagner is a notable figure recognized for his role in establishing the Justice Department.
-
B.
John Wagner
chosen
John Wagner is a British comics writer best known for co-creating the iconic dystopian lawman Judge Dredd for the science fiction anthology 2000 AD.
-
C.
Ron Ellis
Ron Ellis is a former Canadian professional ice hockey right winger best known for his long and successful NHL career with the Toronto Maple Leafs.
-
D.
Pat Mills
Pat Mills is a British comics writer and editor often called the "godfather of British comics," best known for co-creating influential titles like 2000 AD and characters such as Judge Dredd.
-
E.
Peter Milligan
Peter Milligan is a British comic book writer known for his influential, often surreal and character-driven work on titles for DC’s Vertigo imprint and other major publishers.
- 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_69d7bde87b648190bcd0266e9efde098 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954a629fc8190a1c3b6777aad4527 |
completed | April 10, 2026, 7:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6a537bb1881908a50073d4f27b66c |
completed | May 3, 2026, 1:30 a.m. |
Created at: April 9, 2026, 4:44 p.m.