Triple

T2023659
Position Surface form Disambiguated ID Type / Status
Subject Exocet E44159 entity
Predicate typeVariant P4680 FINISHED
Object MM40
MM40 is a long-range, ship- and coastal-defense variant of the French-made Exocet anti-ship missile family.
 E225969 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: MM40 | Statement: [Exocet, typeVariant, MM40]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MM40
Context triple: [Exocet, typeVariant, MM40]
  • A. M44
    M44 is an open star cluster in the constellation Cancer, also known as the Beehive Cluster or Praesepe, and is one of the nearest and most prominent clusters visible to the naked eye.
  • B. MM
    MM is a post-nominal abbreviation indicating that a person has been awarded the Military Medal for bravery in battle.
  • C. Scala MM400
    Scala MM400 is a multimedia authoring and presentation software package for the Amiga platform, widely used for creating interactive graphics, video titling, and information displays.
  • D. BB-45
    BB-45 is the hull classification symbol for USS Colorado, a Colorado-class battleship that served in the United States Navy during the early to mid-20th century, including World War II.
  • E. M1044
    The M1044 is a specific armored variant of the military Humvee designed for enhanced protection and tactical utility in combat environments.
  • 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: MM40
Triple: [Exocet, typeVariant, MM40]
Generated description
MM40 is a long-range, ship- and coastal-defense variant of the French-made Exocet anti-ship missile family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MM40
Target entity description: MM40 is a long-range, ship- and coastal-defense variant of the French-made Exocet anti-ship missile family.
  • A. M44
    M44 is an open star cluster in the constellation Cancer, also known as the Beehive Cluster or Praesepe, and is one of the nearest and most prominent clusters visible to the naked eye.
  • B. MM
    MM is a post-nominal abbreviation indicating that a person has been awarded the Military Medal for bravery in battle.
  • C. Scala MM400
    Scala MM400 is a multimedia authoring and presentation software package for the Amiga platform, widely used for creating interactive graphics, video titling, and information displays.
  • D. BB-45
    BB-45 is the hull classification symbol for USS Colorado, a Colorado-class battleship that served in the United States Navy during the early to mid-20th century, including World War II.
  • E. M1044
    The M1044 is a specific armored variant of the military Humvee designed for enhanced protection and tactical utility in combat environments.
  • 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_69a8891201bc8190aca837be6de41579 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abbdbfe6188190a32ab023660312bd completed March 7, 2026, 5:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae0af7e5b0819088e2221ddc0a38ce completed March 8, 2026, 11:49 p.m.
NEDg Description generation batch_69ae0b78f3fc81909010d88b454e9fa1 completed March 8, 2026, 11:51 p.m.
NED2 Entity disambiguation (via description) batch_69ae0c5983ac819082362a3b67dd9808 completed March 8, 2026, 11:55 p.m.
Created at: March 4, 2026, 7:38 p.m.