Triple

T13998328
Position Surface form Disambiguated ID Type / Status
Subject Chennai Port E336758 entity
Predicate hasPortCode P24997 FINISHED
Object INMAA
INMAA is the UN/LOCODE and port code used to identify Chennai Port, a major maritime gateway on the southeastern coast of India.
 E1074733 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: INMAA | Statement: [Chennai Port, hasPortCode, INMAA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: INMAA
Context triple: [Chennai Port, hasPortCode, INMAA]
  • A. IMAU
    IMAU is the commonly used abbreviation for Inner Mongolia Agricultural University, a higher education institution in China specializing in agricultural and related sciences.
  • B. Imasayi
    Imasayi is a prominent town in Yewa North Local Government Area of Ogun State, southwestern Nigeria.
  • C. Inmeas
    Inmeas is an alternative name for the Isinay language, an Austronesian language spoken by the Isinay people in the Philippines.
  • D. IN-AN
    IN-AN is the ISO 3166-2 code representing the Andaman and Nicobar Islands union territory of India.
  • E. Nimaathap
    Nimaathap was an ancient Egyptian queen of the late 2nd Dynasty, likely a royal consort and mother of early 3rd Dynasty kings.
  • 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: INMAA
Triple: [Chennai Port, hasPortCode, INMAA]
Generated description
INMAA is the UN/LOCODE and port code used to identify Chennai Port, a major maritime gateway on the southeastern coast of India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: INMAA
Target entity description: INMAA is the UN/LOCODE and port code used to identify Chennai Port, a major maritime gateway on the southeastern coast of India.
  • A. IMAU
    IMAU is the commonly used abbreviation for Inner Mongolia Agricultural University, a higher education institution in China specializing in agricultural and related sciences.
  • B. Imasayi
    Imasayi is a prominent town in Yewa North Local Government Area of Ogun State, southwestern Nigeria.
  • C. Inmeas
    Inmeas is an alternative name for the Isinay language, an Austronesian language spoken by the Isinay people in the Philippines.
  • D. IN-AN
    IN-AN is the ISO 3166-2 code representing the Andaman and Nicobar Islands union territory of India.
  • E. Nimaathap
    Nimaathap was an ancient Egyptian queen of the late 2nd Dynasty, likely a royal consort and mother of early 3rd Dynasty kings.
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2eb68ba88190bfaf10777d607bf3 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac9f1f6c8190af7ddac920661bd5 completed May 6, 2026, 9:03 p.m.
NEDg Description generation batch_69fbae3d04f081908c8d28148b4f1de0 completed May 6, 2026, 9:10 p.m.
NED2 Entity disambiguation (via description) batch_69fbaf41636c8190bf44bd238bd9d9a4 completed May 6, 2026, 9:14 p.m.
Created at: April 9, 2026, 10:19 p.m.