Triple
T17737009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Elkins |
E442745
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Inferno
"Inferno" is a 1999 American supernatural horror film edited by Tom Elkins, known for its demonic themes and atmospheric scares.
|
E1285495
|
NE FINISHED |
How this triple was built (4 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: Inferno | Statement: [Tom Elkins, notableWork, Inferno]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Inferno Context triple: [Tom Elkins, notableWork, Inferno]
-
A.
Inferno
Inferno is a distributed operating system developed at Bell Labs, known for its use of the Limbo programming language and its focus on portable, networked computing.
-
B.
Inferno
Inferno is one of the most iconic and strategically complex bomb defusal maps in Counter-Strike, known for its tight chokepoints and intense mid and banana control battles.
-
C.
Inferno
Inferno is the first cantica of Dante Alighieri’s Divine Comedy, depicting the poet’s allegorical journey through the nine circles of Hell.
-
D.
Inferno
"Inferno" is a 1980s action thriller film best known for its desert survival and revenge storyline, directed by John G. Avildsen.
-
E.
Inferno
Inferno is a major expansion for the sci-fi MMORPG EVE Online that focused on revamping warfare mechanics, including factional warfare and mercenary contracts.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Inferno Triple: [Tom Elkins, notableWork, Inferno]
Generated description
"Inferno" is a 1999 American supernatural horror film edited by Tom Elkins, known for its demonic themes and atmospheric scares.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Inferno Target entity description: "Inferno" is a 1999 American supernatural horror film edited by Tom Elkins, known for its demonic themes and atmospheric scares.
-
A.
Inferno
"Inferno" is a critically acclaimed short horror film by visual effects artist and director Mike Hill, known for its atmospheric storytelling and striking, cinematic imagery.
-
B.
Inferno
"Inferno" is a 1980s action thriller film best known for its desert survival and revenge storyline, directed by John G. Avildsen.
-
C.
Inferno
"Inferno" is a 1953 Technicolor 3D film noir thriller starring William Lundigan alongside Robert Ryan and Rhonda Fleming, noted for its desert survival plot and innovative use of 3D cinematography.
-
D.
Inferno
"Inferno" is a 2016 mystery thriller film based on Dan Brown's novel, in which Irrfan Khan plays a key supporting role alongside Tom Hanks.
-
E.
Inferno
Inferno is the third and final episode of the 1995 first-person shooter game The Ultimate Doom, featuring some of the most challenging levels set in a hellish environment.
- F. None of above. chosen
Provenance (5 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e478ec48988190a503f9aafeab6d23 |
completed | April 19, 2026, 6:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0242f965148190a7b76796546ab920 |
completed | May 11, 2026, 8:58 p.m. |
| NEDg | Description generation | batch_6a02455730948190b1151d24f260d768 |
completed | May 11, 2026, 9:08 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0245c34d008190ae029000dc8e9cbc |
completed | May 11, 2026, 9:10 p.m. |
Created at: April 10, 2026, 10:08 a.m.