Triple
T9936559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eddie Kaspbrak |
E192772
|
entity |
| Predicate | closeFriend |
P8712
|
FINISHED |
| Object | Richie Tozier |
E197867
|
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: Richie Tozier | Statement: [Eddie Kaspbrak, closeFriend, Richie Tozier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richie Tozier Context triple: [Eddie Kaspbrak, closeFriend, Richie Tozier]
-
A.
Richie Tozier
chosen
Richie Tozier is a wisecracking, foul-mouthed member of the Losers' Club in Stephen King's horror novel "It," known for using humor to cope with fear and trauma.
-
B.
Richie Roberts
Richie Roberts is a real-life New Jersey detective and prosecutor best known for his role in bringing down drug lord Frank Lucas, a story dramatized in the film "American Gangster."
-
C.
Brad Dorros
Brad Dorros is a film and television producer known for his work on projects such as the thriller "The Fifth Estate."
-
D.
Blaze Tucker
Blaze Tucker is the daughter of reality television star and singer-songwriter Kandi Burruss and her husband Todd Tucker.
-
E.
Richie DiMaso
Richie DiMaso is an ambitious and volatile FBI agent in the film "American Hustle" who drives the high-stakes sting operation at the story’s center.
- 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_69ca82dd978c8190947124ab0d3315ac |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5e4e19881909879b394090d6629 |
completed | April 2, 2026, 12:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d269e28f0081908244f9f469b15ec1 |
completed | April 5, 2026, 1:55 p.m. |
Created at: March 30, 2026, 8:44 p.m.