Triple

T22494337
Position Surface form Disambiguated ID Type / Status
Subject Jaroslav Pelikan E556099 entity
Predicate familyName P18 FINISHED
Object Pelikan
Pelikan is a surname of Slavic origin borne by various notable individuals, including scholars and public figures.
 E1540499 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: Pelikan | Statement: [Jaroslav Pelikan, familyName, Pelikan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pelikan
Context triple: [Jaroslav Pelikan, familyName, Pelikan]
  • A. Magura
    Magura is a town and district headquarters in southwestern Bangladesh known for its agricultural surroundings and location within the Khulna Division.
  • B. Magura
    Magura is a mountain peak in the Kysucké Beskydy range of northern Slovakia, known for its forested slopes and scenic hiking routes.
  • C. Braun-Pivet
    Braun-Pivet is the surname of Yaël Braun-Pivet, a prominent French politician who has served as President of the National Assembly.
  • D. Gamo
    Gamo is an Omotic language spoken primarily by the Gamo people in southwestern Ethiopia.
  • E. Mermoz
    Mermoz is a residential neighborhood in Lyon, France, known for its post-war urban development and diverse population within the city’s 8th arrondissement.
  • 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: Pelikan
Triple: [Jaroslav Pelikan, familyName, Pelikan]
Generated description
Pelikan is a surname of Slavic origin borne by various notable individuals, including scholars and public figures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pelikan
Target entity description: Pelikan is a surname of Slavic origin borne by various notable individuals, including scholars and public figures.
  • A. Magura
    Magura is a town and district headquarters in southwestern Bangladesh known for its agricultural surroundings and location within the Khulna Division.
  • B. Magura
    Magura is a mountain peak in the Kysucké Beskydy range of northern Slovakia, known for its forested slopes and scenic hiking routes.
  • C. Braun-Pivet
    Braun-Pivet is the surname of Yaël Braun-Pivet, a prominent French politician who has served as President of the National Assembly.
  • D. Gamo
    Gamo is an Omotic language spoken primarily by the Gamo people in southwestern Ethiopia.
  • E. Mermoz
    Mermoz is a residential neighborhood in Lyon, France, known for its post-war urban development and diverse population within the city’s 8th arrondissement.
  • 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_69e11e5445bc8190b6a9481926db3355 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15cb0dfb88190a4175e5e95d7ad4b completed April 29, 2026, 1:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b17dfe7f48190a0879581d3e4d80f completed May 18, 2026, 1:45 p.m.
NEDg Description generation batch_6a0b18d9beec8190b890e127c62b2ef6 completed May 18, 2026, 1:49 p.m.
NED2 Entity disambiguation (via description) batch_6a0b19953e248190b599854dc58771a0 completed May 18, 2026, 1:52 p.m.
Created at: April 16, 2026, 8:49 p.m.