Triple
T8918813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louis Creed |
E212358
|
entity |
| Predicate | neighbor |
P350
|
FINISHED |
| Object | Jud Crandall |
E212362
|
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: Jud Crandall | Statement: [Louis Creed, neighbor, Jud Crandall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jud Crandall Context triple: [Louis Creed, neighbor, Jud Crandall]
-
A.
Jud Crandall
chosen
Jud Crandall is a central character in Stephen King’s horror novel "Pet Sematary," known as the elderly neighbor who reveals the dark secrets of the cursed burial ground.
-
B.
Court Crandall
Court Crandall is an American screenwriter and creative director best known for co-writing the comedy film "Old School" and for his work in advertising and film.
-
C.
Ross Nordeen
Ross Nordeen is a professional associated with xAI, Elon Musk’s artificial intelligence company.
-
D.
Tom Drysdale
Tom Drysdale is a notable individual recognized as a prominent bearer of the Drysdale surname.
-
E.
Butch Coolidge
Butch Coolidge is a tough, aging boxer in the film "Pulp Fiction" who becomes entangled in a violent series of events after double-crossing a crime boss.
- 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_69ca8393b1808190bd4336787ffa2c40 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6613639881909090d060f388a865 |
completed | April 1, 2026, 12:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfba49d65c8190b9d9908822198cc0 |
completed | April 3, 2026, 1:02 p.m. |
Created at: March 30, 2026, 6:56 p.m.