Triple

T16940141
Position Surface form Disambiguated ID Type / Status
Subject Abó E410928 entity
Predicate hasNameVariant P457 FINISHED
Object Abo
Abo is a variant spelling of the name Abó, which can refer to various places or personal names in different cultural and linguistic contexts.
 E1241954 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: Abo | Statement: [Abó, hasNameVariant, Abo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Abo
Context triple: [Abó, hasNameVariant, Abo]
  • A. Abur
    Abur is the traditional name for the Old Permic alphabet, an early writing system used for the Komi language in the medieval Perm region of Russia.
  • B. Abure
    Abure is a Central Tano language spoken primarily in Côte d’Ivoire by the Abure people.
  • C. Abis
    Abis is a standardized GSM interface that connects a base transceiver station (BTS) to its base station controller (BSC) for managing radio resources and signaling.
  • D. Abele
    Abele is a surname most notably associated with Julian Abele, a pioneering African American architect who contributed to the design of many prominent buildings in the early 20th century.
  • E. Abas
    Abas is a figure in Greek mythology known primarily as the son of Hypermnestra and a king of Argos in some traditions.
  • 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: Abo
Triple: [Abó, hasNameVariant, Abo]
Generated description
Abo is a variant spelling of the name Abó, which can refer to various places or personal names in different cultural and linguistic contexts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Abo
Target entity description: Abo is a variant spelling of the name Abó, which can refer to various places or personal names in different cultural and linguistic contexts.
  • A. Abur
    Abur is the traditional name for the Old Permic alphabet, an early writing system used for the Komi language in the medieval Perm region of Russia.
  • B. Abure
    Abure is a Central Tano language spoken primarily in Côte d’Ivoire by the Abure people.
  • C. Abis
    Abis is a standardized GSM interface that connects a base transceiver station (BTS) to its base station controller (BSC) for managing radio resources and signaling.
  • D. Abele
    Abele is a surname most notably associated with Julian Abele, a pioneering African American architect who contributed to the design of many prominent buildings in the early 20th century.
  • E. Abas
    Abas is a figure in Greek mythology known primarily as the son of Hypermnestra and a king of Argos in some traditions.
  • 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_69d886c886688190967be07322597ac9 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3cfacdbc48190988ac259712bb9e8 completed April 18, 2026, 6:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00cfe7e75881908f95b1d859dd67e4 completed May 10, 2026, 6:35 p.m.
NEDg Description generation batch_6a00d0b13f1c819091f3f8b966e36214 completed May 10, 2026, 6:38 p.m.
NED2 Entity disambiguation (via description) batch_6a00d1ad6b7081908be76d70ad9e2075 completed May 10, 2026, 6:42 p.m.
Created at: April 10, 2026, 5:31 a.m.