Triple
T14659134
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scott Spiegel |
E344188
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Hostel |
E895535
|
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: Hostel | Statement: [Scott Spiegel, notableWork, Hostel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hostel Context triple: [Scott Spiegel, notableWork, Hostel]
-
A.
Hostel
chosen
"Hostel" is a 2005 horror film directed by Eli Roth, known for its graphic violence and role in popularizing the "torture porn" subgenre.
-
B.
Hostel: Part II
Hostel: Part II is a 2007 American horror film and sequel to Hostel, known for its graphic violence and continuation of the "torture porn" subgenre.
-
C.
The Host
The Host is a 2013 science fiction film, based on Stephenie Meyer’s novel, in which Diane Kruger plays a key role in a future where alien “souls” have taken over human bodies.
-
D.
The Host
The Host is a character in the action-strategy game Minecraft Legends who guides and assists the player as they defend the Overworld from invading Piglins.
-
E.
The Host
The Host is the outspoken, jovial innkeeper in Geoffrey Chaucer’s "The Canterbury Tales" who proposes and oversees the storytelling contest among the pilgrims.
- 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_69d822e283fc8190a0e4c235cf880052 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb51b6a248190a44050c0e0ec2d16 |
completed | April 14, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdd5e01cd081909c71fdcf67c3b1f5 |
completed | May 8, 2026, 12:24 p.m. |
Created at: April 10, 2026, 1:27 a.m.