Triple

T18834596
Position Surface form Disambiguated ID Type / Status
Subject Mike MacLean E460625 entity
Predicate notableWork P4 FINISHED
Object 2 Lava 2 Lantula!
2 Lava 2 Lantula! is a 2016 comedic science-fiction disaster film and sequel to Lavalantula, featuring giant fire-breathing spiders wreaking havoc.
E1345913 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: 2 Lava 2 Lantula! | Statement: [Mike MacLean, notableWork, 2 Lava 2 Lantula!]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 2 Lava 2 Lantula!
Context triple: [Mike MacLean, notableWork, 2 Lava 2 Lantula!]
  • A. Lava Lava
    Lava Lava is a Tanzanian Bongo Flava singer and songwriter known for his romantic hits and for being signed to the WCB Wasafi record label founded by Diamond Platnumz.
  • B. Lava Bangers
    Lava Bangers is an instrumental hip-hop album by producer Lazerbeak, known for its hard-hitting beats and genre-blending production.
  • C. Lava
    Lava is a small hill town in West Bengal, India, known as a gateway to the Neora Valley National Park and for its cool climate and forested surroundings.
  • D. Lava
    "Lava" is a nonfiction book by Andrea Warren that explores the science, danger, and human stories surrounding volcanic eruptions.
  • E. Lava
    Lava is a legendary prince in the Hindu epic Ramayana, known as one of the twin sons of Rama and Sita.
  • 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: 2 Lava 2 Lantula!
Triple: [Mike MacLean, notableWork, 2 Lava 2 Lantula!]
Generated description
2 Lava 2 Lantula! is a 2016 comedic science-fiction disaster film and sequel to Lavalantula, featuring giant fire-breathing spiders wreaking havoc.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 2 Lava 2 Lantula!
Target entity description: 2 Lava 2 Lantula! is a 2016 comedic science-fiction disaster film and sequel to Lavalantula, featuring giant fire-breathing spiders wreaking havoc.
  • A. Lava Lava
    Lava Lava is a Tanzanian Bongo Flava singer and songwriter known for his romantic hits and for being signed to the WCB Wasafi record label founded by Diamond Platnumz.
  • B. Lava Bangers
    Lava Bangers is an instrumental hip-hop album by producer Lazerbeak, known for its hard-hitting beats and genre-blending production.
  • C. Lava
    "Lava" is a nonfiction book by Andrea Warren that explores the science, danger, and human stories surrounding volcanic eruptions.
  • D. Lava
    Lava is a legendary prince in the Hindu epic Ramayana, known as one of the twin sons of Rama and Sita.
  • E. Lava
    Lava is a small hill town in West Bengal, India, known as a gateway to the Neora Valley National Park and for its cool climate and forested surroundings.
  • 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a99c1394819095c62eef040e552c completed April 20, 2026, 4:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05676957848190bbc1998f4e36d11e completed May 14, 2026, 6:10 a.m.
NEDg Description generation batch_6a056984d9d88190ab457cef689a5159 completed May 14, 2026, 6:19 a.m.
NED2 Entity disambiguation (via description) batch_6a0569fd03f081908d217efa260f8938 completed May 14, 2026, 6:21 a.m.
Created at: April 10, 2026, 11:56 a.m.