Triple

T15198224
Position Surface form Disambiguated ID Type / Status
Subject Ticao Island E363193 entity
Predicate hasDiveSite P41537 FINISHED
Object Manta Bowl
Manta Bowl is a renowned dive site off Ticao Island in the Philippines, famous for strong currents that attract manta rays and other pelagic marine life.
E1142870 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: Manta Bowl | Statement: [Ticao Island, hasDiveSite, Manta Bowl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manta Bowl
Context triple: [Ticao Island, hasDiveSite, Manta Bowl]
  • A. Manta Rota
    Manta Rota is a coastal village and popular beach resort in Portugal’s Algarve region, known for its long sandy beach and calm, shallow waters.
  • B. Manta
    Manta is a municipality located in Almeidas Province in the Cundinamarca Department of central Colombia.
  • C. Manta
    Manta is a distributed object storage and compute service designed for running parallel computations directly on stored data in the cloud.
  • D. Manta
    Manta is a major coastal city and important seaport in western Ecuador, known for its fishing industry, beaches, and commercial activity.
  • E. Manta
    Manta is a flying roller coaster at SeaWorld Orlando that simulates the graceful, gliding motion of a manta ray through a combination of high-speed thrills and aquatic theming.
  • 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: Manta Bowl
Triple: [Ticao Island, hasDiveSite, Manta Bowl]
Generated description
Manta Bowl is a renowned dive site off Ticao Island in the Philippines, famous for strong currents that attract manta rays and other pelagic marine life.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Manta Bowl
Target entity description: Manta Bowl is a renowned dive site off Ticao Island in the Philippines, famous for strong currents that attract manta rays and other pelagic marine life.
  • A. Manta Rota
    Manta Rota is a coastal village and popular beach resort in Portugal’s Algarve region, known for its long sandy beach and calm, shallow waters.
  • B. Manta
    Manta is a major coastal city and important seaport in western Ecuador, known for its fishing industry, beaches, and commercial activity.
  • C. Manta
    Manta is a flying roller coaster at SeaWorld Orlando that simulates the graceful, gliding motion of a manta ray through a combination of high-speed thrills and aquatic theming.
  • D. Manta
    Manta is a distributed object storage and compute service designed for running parallel computations directly on stored data in the cloud.
  • E. Manta
    Manta is a municipality located in Almeidas Province in the Cundinamarca Department of central Colombia.
  • 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e006b476208190a5119710c518bb1f completed April 15, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69fed3342624819087be35acadd88136 completed May 9, 2026, 6:24 a.m.
NEDg Description generation batch_69fed516a2008190bab6da27d28289e7 completed May 9, 2026, 6:32 a.m.
NED2 Entity disambiguation (via description) batch_69fed57659a081909ec777549deff505 completed May 9, 2026, 6:34 a.m.
Created at: April 10, 2026, 3:10 a.m.