Triple

T7841337
Position Surface form Disambiguated ID Type / Status
Subject Marau language E181809 entity
Predicate glottologName P6521 FINISHED
Object Marau
Marau is an Oceanic language spoken by a small community in Papua New Guinea.
 E705582 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: Marau | Statement: [Marau language, glottologName, Marau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marau
Context triple: [Marau language, glottologName, Marau]
  • A. Marum
    Marum is a former municipality in the Dutch province of Groningen that became part of the larger municipality of Westerkwartier after an administrative reorganization.
  • B. Marum
    Marum is one of the main active volcanic craters on Ambrym Island in Vanuatu, known for its persistent lava lake and dramatic eruptions.
  • C. Marapu
    Marapu is the indigenous ancestral belief system of the Sumbanese people, characterized by animism, ancestor worship, and elaborate ritual practices.
  • D. Marangona
    Marangona is the largest and most famous bell of St Mark's Campanile in Venice, traditionally used to mark the beginning and end of the working day and to signal important civic events.
  • E. Marajil
    Marajil was the mother of the Abbasid caliph al-Ma'mun and a woman of the early ninth-century Abbasid court.
  • 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: Marau
Triple: [Marau language, glottologName, Marau]
Generated description
Marau is an Oceanic language spoken by a small community in Papua New Guinea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marau
Target entity description: Marau is an Oceanic language spoken by a small community in Papua New Guinea.
  • A. Marum
    Marum is a former municipality in the Dutch province of Groningen that became part of the larger municipality of Westerkwartier after an administrative reorganization.
  • B. Marum
    Marum is one of the main active volcanic craters on Ambrym Island in Vanuatu, known for its persistent lava lake and dramatic eruptions.
  • C. Marapu
    Marapu is the indigenous ancestral belief system of the Sumbanese people, characterized by animism, ancestor worship, and elaborate ritual practices.
  • D. Marangona
    Marangona is the largest and most famous bell of St Mark's Campanile in Venice, traditionally used to mark the beginning and end of the working day and to signal important civic events.
  • E. Marajil
    Marajil was the mother of the Abbasid caliph al-Ma'mun and a woman of the early ninth-century Abbasid court.
  • 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_69ca8285d6488190a95d4c02d7354b53 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb14c6cbe48190b73df491de1004c3 completed March 31, 2026, 12:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbdf0dee3881908f817427143cf774 completed March 31, 2026, 2:49 p.m.
NEDg Description generation batch_69cc46bca04481908852425c214a4e34 completed March 31, 2026, 10:12 p.m.
NED2 Entity disambiguation (via description) batch_69cc49129e188190aaebd6a1188788d9 completed March 31, 2026, 10:22 p.m.
Created at: March 30, 2026, 4:47 p.m.