Triple

T1351994
Position Surface form Disambiguated ID Type / Status
Subject Vanuatu languages E28901 entity
Predicate includesLanguage P2177 FINISHED
Object Unua
Unua is an Oceanic language spoken by a small community in Vanuatu.
 E153878 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: Unua | Statement: [Vanuatu languages, includesLanguage, Unua]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Unua
Context triple: [Vanuatu languages, includesLanguage, Unua]
  • A. Mwanza
    Mwanza is a major port city in northwestern Tanzania, situated on the southern shores of Lake Victoria and serving as a key commercial and transport hub for the region.
  • B. Quo primum
    Quo primum is the 1570 papal bull of Pope Pius V that standardized the Roman Rite liturgy and mandated the widespread use of what became known as the Tridentine Mass.
  • C. La Première
    La Première is Air France’s ultra-luxury first-class cabin, known for its exclusive suites, refined service, and premium amenities on select long-haul routes.
  • D. La Première
    La Première is a Swiss French-language public radio station operated by Radio Télévision Suisse, offering news, culture, and talk programming.
  • E. La Première
    La Première is a French public television network of regional channels serving France’s overseas departments and territories, operated by the national broadcaster France Télévisions.
  • 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: Unua
Triple: [Vanuatu languages, includesLanguage, Unua]
Generated description
Unua is an Oceanic language spoken by a small community in Vanuatu.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Unua
Target entity description: Unua is an Oceanic language spoken by a small community in Vanuatu.
  • A. Mwanza
    Mwanza is a major port city in northwestern Tanzania, situated on the southern shores of Lake Victoria and serving as a key commercial and transport hub for the region.
  • B. Quo primum
    Quo primum is the 1570 papal bull of Pope Pius V that standardized the Roman Rite liturgy and mandated the widespread use of what became known as the Tridentine Mass.
  • C. La Première
    La Première is a Swiss French-language public radio station operated by Radio Télévision Suisse, offering news, culture, and talk programming.
  • D. La Première
    La Première is Air France’s ultra-luxury first-class cabin, known for its exclusive suites, refined service, and premium amenities on select long-haul routes.
  • E. La Première
    La Première is a French public television network of regional channels serving France’s overseas departments and territories, operated by the national broadcaster France Télévisions.
  • 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_69a498571d248190a0ac9eb02d97097f completed March 1, 2026, 7:49 p.m.
NER Named-entity recognition batch_69a4c26b1b4881908ae4b1b2c9b268a0 completed March 1, 2026, 10:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69acc63eef908190aef058396f63a5a4 completed March 8, 2026, 12:43 a.m.
NEDg Description generation batch_69acc6dd15a481908cf870c87d469bc9 completed March 8, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_69acc8072bb08190b1b7fb19fc2c0efc completed March 8, 2026, 12:51 a.m.
Created at: March 1, 2026, 7:56 p.m.