Triple

T9284062
Position Surface form Disambiguated ID Type / Status
Subject Martin E223140 entity
Predicate hasVariant P455 FINISHED
Object Martim
Martim is a given name, primarily used in Portuguese-speaking countries, that corresponds to the variant Martin.
E789310 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: Martim | Statement: [Martin, hasVariant, Martim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martim
Context triple: [Martin, hasVariant, Martim]
  • A. Martim Longo
    Martim Longo is a village and civil parish in the municipality of Alcoutim in the Algarve region of southern Portugal.
  • B. Ilmandu
    Ilmandu is a small village in northern Estonia that forms part of Harku Parish near the capital city, Tallinn.
  • C. Martis
    Martis is a small town and comune in the Gallura region of northern Sardinia, Italy.
  • D. Catreus
    Catreus is a figure in Greek mythology, a son of King Minos of Crete whose tragic fate is tied to a prophecy that he would be killed by one of his own children.
  • E. Balnibarbi
    Balnibarbi is a fictional country in Jonathan Swift's satirical novel "Gulliver's Travels," known for its absurd scientific experiments and mismanaged society.
  • 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: Martim
Triple: [Martin, hasVariant, Martim]
Generated description
Martim is a given name, primarily used in Portuguese-speaking countries, that corresponds to the variant Martin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Martim
Target entity description: Martim is a given name, primarily used in Portuguese-speaking countries, that corresponds to the variant Martin.
  • A. Martim Longo
    Martim Longo is a village and civil parish in the municipality of Alcoutim in the Algarve region of southern Portugal.
  • B. Ilmandu
    Ilmandu is a small village in northern Estonia that forms part of Harku Parish near the capital city, Tallinn.
  • C. Martis
    Martis is a small town and comune in the Gallura region of northern Sardinia, Italy.
  • D. Catreus
    Catreus is a figure in Greek mythology, a son of King Minos of Crete whose tragic fate is tied to a prophecy that he would be killed by one of his own children.
  • E. Balnibarbi
    Balnibarbi is a fictional country in Jonathan Swift's satirical novel "Gulliver's Travels," known for its absurd scientific experiments and mismanaged society.
  • 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_69ca842123588190b3f2e1a69037d141 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd081e72988190917f425e64631837 completed April 1, 2026, 11:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0b21d8f1081909b2493151fde4a5f completed April 4, 2026, 6:39 a.m.
NEDg Description generation batch_69d0b3234d088190a8ed13b4d4772fb5 completed April 4, 2026, 6:43 a.m.
NED2 Entity disambiguation (via description) batch_69d0b3bcd5548190ba1af3d0fa72780a completed April 4, 2026, 6:46 a.m.
Created at: March 30, 2026, 7:34 p.m.