Triple
T8319675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horns (film) |
E194797
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object | Merrin Williams |
E760568
|
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: Merrin Williams | Statement: [Horns (film), character, Merrin Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Merrin Williams Context triple: [Horns (film), character, Merrin Williams]
-
A.
Merrin Williams
chosen
Merrin Williams is a central character in Joe Hill's dark fantasy novel "Horns," known as the murdered girlfriend whose death drives the story's supernatural revenge plot.
-
B.
Lindsay Merrill
Lindsay Merrill is an individual notable enough to be recognized as a namesake or prominent bearer of the surname Merrill.
-
C.
Shannon Doughton
Shannon Doughton is a musician best known as a principal performer associated with the band Pod.
-
D.
Lindsay Mills
Lindsay Mills is an American acrobat, dancer, and blogger best known as the longtime partner of NSA whistleblower Edward Snowden.
-
E.
Milynn Sarley
Milynn Sarley is an American actress and internet personality known for her roles in low-budget fantasy and action films as well as her presence in online geek and gaming communities.
- 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_69ca82e7a8a88190a32bb5cc0feb012d |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7f6686a0819094abc2bfd2e500a5 |
completed | March 31, 2026, 8:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfab01c58c81909148dacad2dc7667 |
completed | April 3, 2026, 11:56 a.m. |
Created at: March 30, 2026, 5:55 p.m.