Triple

T23050791
Position Surface form Disambiguated ID Type / Status
Subject Shefa Province E574005 entity
Predicate contains P35 FINISHED
Object Mataso
Mataso is a small island in Vanuatu located within Shefa Province in the central South Pacific.
E1569627 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: Mataso | Statement: [Shefa Province, contains, Mataso]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mataso
Context triple: [Shefa Province, contains, Mataso]
  • A. Kimeru
    Kimeru is a Bantu language spoken primarily by the Meru people of central Kenya.
  • B. Mangole
    Mangole is one of the principal islands of Indonesia’s Sula Islands archipelago in North Maluku Province.
  • C. Musanga
    Musanga is a small genus of fast-growing tropical African trees in the nettle family, best known for the umbrella tree (Musanga cecropioides) commonly found in rainforest and disturbed habitats.
  • D. Mbini
    Mbini is a town in mainland Equatorial Guinea situated along the Benito River, known historically as a small river port and local administrative center.
  • E. Mwenga
    Mwenga is a town in the South Kivu province of the Democratic Republic of the Congo that serves as an administrative and commercial center for the surrounding region.
  • 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: Mataso
Triple: [Shefa Province, contains, Mataso]
Generated description
Mataso is a small island in Vanuatu located within Shefa Province in the central South Pacific.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mataso
Target entity description: Mataso is a small island in Vanuatu located within Shefa Province in the central South Pacific.
  • A. Kimeru
    Kimeru is a Bantu language spoken primarily by the Meru people of central Kenya.
  • B. Mangole
    Mangole is one of the principal islands of Indonesia’s Sula Islands archipelago in North Maluku Province.
  • C. Musanga
    Musanga is a small genus of fast-growing tropical African trees in the nettle family, best known for the umbrella tree (Musanga cecropioides) commonly found in rainforest and disturbed habitats.
  • D. Mbini
    Mbini is a town in mainland Equatorial Guinea situated along the Benito River, known historically as a small river port and local administrative center.
  • E. Mwenga
    Mwenga is a town in the South Kivu province of the Democratic Republic of the Congo that serves as an administrative and commercial center for the surrounding region.
  • 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_69e245b9c11481909d06c872214d21af completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1867c443081909588262bc90748af completed April 29, 2026, 4:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c15a203ac8190b5f2df1cf0a88ac5 completed May 19, 2026, 7:47 a.m.
NEDg Description generation batch_6a0c16ad0b7c8190bde9d5e8ba0efb5b completed May 19, 2026, 7:52 a.m.
NED2 Entity disambiguation (via description) batch_6a0c17da6a108190b37d1e69e6f24e00 completed May 19, 2026, 7:57 a.m.
Created at: April 17, 2026, 3:54 p.m.