Triple

T718469
Position Surface form Disambiguated ID Type / Status
Subject Rami Malek E14361 entity
Predicate notableWork P4 FINISHED
Object Until Dawn
Until Dawn is a cinematic survival horror video game that follows a group of teenagers trapped on a remote mountain, where player choices determine who survives until morning.
 E85417 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: Until Dawn | Statement: [Rami Malek, notableWork, Until Dawn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Until Dawn
Context triple: [Rami Malek, notableWork, Until Dawn]
  • A. Save the Night
    "Save the Night" is a song by John Legend from his R&B album "Love in the Future."
  • B. Lurking Fear
    Lurking Fear is a renowned big-wall rock climbing route on Yosemite’s El Capitan, known for its long, challenging aid and free climbing pitches.
  • C. Relic
    Relic is a fashion accessories brand under Fossil Group known for its affordable, casual watches, handbags, and small leather goods.
  • D. Edith Finch
    Edith Finch was the first wife of philosopher Bertrand Russell, known primarily for her marriage into the prominent Russell family.
  • E. Let the Right One In
    Let the Right One In is a critically acclaimed 2008 Swedish romantic horror film about the bond between a bullied boy and a mysterious child vampire.
  • 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: Until Dawn
Triple: [Rami Malek, notableWork, Until Dawn]
Generated description
Until Dawn is a cinematic survival horror video game that follows a group of teenagers trapped on a remote mountain, where player choices determine who survives until morning.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Until Dawn
Target entity description: Until Dawn is a cinematic survival horror video game that follows a group of teenagers trapped on a remote mountain, where player choices determine who survives until morning.
  • A. Save the Night
    "Save the Night" is a song by John Legend from his R&B album "Love in the Future."
  • B. Lurking Fear
    Lurking Fear is a renowned big-wall rock climbing route on Yosemite’s El Capitan, known for its long, challenging aid and free climbing pitches.
  • C. Relic
    Relic is a fashion accessories brand under Fossil Group known for its affordable, casual watches, handbags, and small leather goods.
  • D. Edith Finch
    Edith Finch was the first wife of philosopher Bertrand Russell, known primarily for her marriage into the prominent Russell family.
  • E. Let the Right One In
    Let the Right One In is a critically acclaimed 2008 Swedish romantic horror film about the bond between a bullied boy and a mysterious child vampire.
  • 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_69a4934a36e081909e7abef98b898a4e completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a58d4c3c8190ad4527d14bca5e6e completed March 1, 2026, 8:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5dcb77bc481909d79542001fafbd2 completed March 2, 2026, 6:53 p.m.
NEDg Description generation batch_69a5de57bbec81908a5d1202299194f4 completed March 2, 2026, 7 p.m.
NED2 Entity disambiguation (via description) batch_69a60952c6388190a23a178d695eec6e completed March 2, 2026, 10:04 p.m.
Created at: March 1, 2026, 7:37 p.m.