Triple

T9968405
Position Surface form Disambiguated ID Type / Status
Subject Dolph Lundgren E195740 entity
Predicate knownFor P22 FINISHED
Object Red Scorpion
Red Scorpion is a 1988 Cold War–era action film starring Dolph Lundgren as a Soviet special forces officer sent to assassinate an African rebel leader.
E832067 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: Red Scorpion | Statement: [Dolph Lundgren, knownFor, Red Scorpion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Red Scorpion
Context triple: [Dolph Lundgren, knownFor, Red Scorpion]
  • A. Scorpion II
    Scorpion II was a predynastic Egyptian ruler, likely a king of Upper Egypt, who reigned shortly before the unification of Egypt under Narmer.
  • B. Strike Back
    Strike Back is a British action–drama television series centered on covert military operations and counterterrorism missions around the world.
  • C. License to Kill
    "License to Kill" is a 1989 James Bond film best known for its darker tone and for featuring the title song performed by soul singer Gladys Knight.
  • D. Red Heat
    Red Heat is a 1988 buddy-cop action film starring Arnold Schwarzenegger and James Belushi, directed by Walter Hill.
  • E. Killer Force
    Killer Force is a 1976 action-thriller film about a security chief investigating a suspected diamond heist at a South African mine.
  • 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: Red Scorpion
Triple: [Dolph Lundgren, knownFor, Red Scorpion]
Generated description
Red Scorpion is a 1988 Cold War–era action film starring Dolph Lundgren as a Soviet special forces officer sent to assassinate an African rebel leader.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Red Scorpion
Target entity description: Red Scorpion is a 1988 Cold War–era action film starring Dolph Lundgren as a Soviet special forces officer sent to assassinate an African rebel leader.
  • A. Scorpion II
    Scorpion II was a predynastic Egyptian ruler, likely a king of Upper Egypt, who reigned shortly before the unification of Egypt under Narmer.
  • B. Strike Back
    Strike Back is a British action–drama television series centered on covert military operations and counterterrorism missions around the world.
  • C. License to Kill
    "License to Kill" is a 1989 James Bond film best known for its darker tone and for featuring the title song performed by soul singer Gladys Knight.
  • D. Red Heat
    Red Heat is a 1988 buddy-cop action film starring Arnold Schwarzenegger and James Belushi, directed by Walter Hill.
  • E. Killer Force
    Killer Force is a 1976 action-thriller film about a security chief investigating a suspected diamond heist at a South African mine.
  • 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_69ca82ebd1288190912f9e4482d1fa35 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb7b683ac8190ac97bd775a860d29 completed April 2, 2026, 12:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23db701b881909bb986a32df4349b completed April 5, 2026, 10:47 a.m.
NEDg Description generation batch_69d23f35049c8190a71a88f5dd686596 completed April 5, 2026, 10:53 a.m.
NED2 Entity disambiguation (via description) batch_69d24097d4008190b7a9e7638cd9a972 completed April 5, 2026, 10:59 a.m.
Created at: March 30, 2026, 8:47 p.m.