Triple
T19365681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freddy vs. Jason |
E484394
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Freddy Krueger |
—
|
NE NERFINISHED |
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: Freddy Krueger | Statement: [Freddy vs. Jason, featuresCharacter, Freddy Krueger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Freddy Krueger Context triple: [Freddy vs. Jason, featuresCharacter, Freddy Krueger]
-
A.
Freddy Krueger
chosen
Freddy Krueger is a fictional supernatural serial killer known for haunting and murdering teenagers in their dreams, recognizable by his burned face, bladed glove, and striped sweater.
-
B.
Jason Voorhees
Jason Voorhees is a fictional, hockey mask–wearing serial killer and horror icon best known as the central antagonist of the Friday the 13th slasher film series.
-
C.
Michael Myers
Michael Myers is the iconic masked serial killer from the "Halloween" horror film franchise.
-
D.
Willis Hale
Willis Hale was an American architect known for his highly ornate and eccentric Victorian-era buildings in Philadelphia.
-
E.
Gretchen Krueger
Gretchen Krueger is a researcher and author known for her work on CLIP, a multimodal AI model that connects images and text.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d305088190ad13571532aa454c |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e619aa9ff48190b1ede47fb88a682e |
completed | April 20, 2026, 12:18 p.m. |
Created at: April 10, 2026, 1:35 p.m.