Triple
T12146831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laura Harris |
E289346
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Severed
Severed is a 2005 Canadian horror film about a group of people trapped on a logging site after a virus outbreak turns workers into zombies.
|
E965494
|
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: Severed | Statement: [Laura Harris, notableWork, Severed]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Severed Context triple: [Laura Harris, notableWork, Severed]
-
A.
Ravage
Ravage is a Decepticon spy and attack beast in the Transformers franchise, typically depicted as a stealthy, feline-like robot that specializes in infiltration and reconnaissance.
-
B.
Die by the Sword
Die by the Sword is a 1998 fantasy action-adventure video game known for its innovative, physics-based sword-fighting system that allowed precise control of weapon movements.
-
C.
Frenzy
"Frenzy" is a popular Nigerian Afropop song by artist D'Prince, known for its energetic beat and club-friendly vibe.
-
D.
Frenzy
Frenzy is a Hearthstone keyword that triggers a special effect the first time a minion survives damage.
-
E.
Frenzy
Frenzy is a 1972 British thriller film directed by Alfred Hitchcock, known for its dark humor and disturbing portrayal of a serial killer in London.
- 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: Severed Triple: [Laura Harris, notableWork, Severed]
Generated description
Severed is a 2005 Canadian horror film about a group of people trapped on a logging site after a virus outbreak turns workers into zombies.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Severed Target entity description: Severed is a 2005 Canadian horror film about a group of people trapped on a logging site after a virus outbreak turns workers into zombies.
-
A.
Ravage
Ravage is a Decepticon spy and attack beast in the Transformers franchise, typically depicted as a stealthy, feline-like robot that specializes in infiltration and reconnaissance.
-
B.
Die by the Sword
Die by the Sword is a 1998 fantasy action-adventure video game known for its innovative, physics-based sword-fighting system that allowed precise control of weapon movements.
-
C.
Frenzy
"Frenzy" is a popular Nigerian Afropop song by artist D'Prince, known for its energetic beat and club-friendly vibe.
-
D.
Frenzy
Frenzy is a Hearthstone keyword that triggers a special effect the first time a minion survives damage.
-
E.
Frenzy
Frenzy is a 1972 British thriller film directed by Alfred Hitchcock, known for its dark humor and disturbing portrayal of a serial killer in London.
- 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_69d6ab4c6710819097a9d228382dde43 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915ac2ebc81909155f9b2fb4a2252 |
completed | April 10, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f696ec648190aa43655ac8a2b312 |
completed | May 2, 2026, 1:05 p.m. |
| NEDg | Description generation | batch_69f600b7385881909ddb86a1d39ff5d4 |
completed | May 2, 2026, 1:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f601ebaa448190ba59485d9d7d68d1 |
completed | May 2, 2026, 1:53 p.m. |
Created at: April 8, 2026, 9:49 p.m.