Triple

T21154984
Position Surface form Disambiguated ID Type / Status
Subject Mika Špiljak E521287 entity
Predicate familyName P18 FINISHED
Object Špiljak
Špiljak is a Croatian surname most notably associated with Mika Špiljak, a prominent Yugoslav and Croatian communist politician and former President of Yugoslavia.
E1469666 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: Špiljak | Statement: [Mika Špiljak, familyName, Špiljak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Špiljak
Context triple: [Mika Špiljak, familyName, Špiljak]
  • A. Krajišnik
    Krajišnik is a village located within the Temerin municipality in the Vojvodina region of northern Serbia.
  • B. Ojdanić
    Ojdanić is a Serbian surname most notably associated with Dragoljub Ojdanić, a former Yugoslav Army general and political figure.
  • C. Jakšić
    Jakšić is a municipality and settlement in eastern Croatia, located in Požega-Slavonia County.
  • D. Lukač
    Lukač is a municipality and settlement in northern Croatia, located within Virovitica-Podravina County.
  • E. Rošnjak
    Rošnjak is a small, secluded waterfall located within Croatia’s Krka National Park, known for its tranquil setting and natural beauty.
  • 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: Špiljak
Triple: [Mika Špiljak, familyName, Špiljak]
Generated description
Špiljak is a Croatian surname most notably associated with Mika Špiljak, a prominent Yugoslav and Croatian communist politician and former President of Yugoslavia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Špiljak
Target entity description: Špiljak is a Croatian surname most notably associated with Mika Špiljak, a prominent Yugoslav and Croatian communist politician and former President of Yugoslavia.
  • A. Krajišnik
    Krajišnik is a village located within the Temerin municipality in the Vojvodina region of northern Serbia.
  • B. Ojdanić
    Ojdanić is a Serbian surname most notably associated with Dragoljub Ojdanić, a former Yugoslav Army general and political figure.
  • C. Jakšić
    Jakšić is a municipality and settlement in eastern Croatia, located in Požega-Slavonia County.
  • D. Lukač
    Lukač is a municipality and settlement in northern Croatia, located within Virovitica-Podravina County.
  • E. Rošnjak
    Rošnjak is a small, secluded waterfall located within Croatia’s Krka National Park, known for its tranquil setting and natural beauty.
  • 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_69e0b50d1ea481909c07e63c3ead9316 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7252a48788190bfdfe811fc6cfc06 completed April 21, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a096dca1b28819087d3d6d118e7eaee completed May 17, 2026, 7:27 a.m.
NEDg Description generation batch_6a096e6cce748190ba618dfe86f7f6ce completed May 17, 2026, 7:29 a.m.
NED2 Entity disambiguation (via description) batch_6a096f7706448190a1bb61535e0adcd3 completed May 17, 2026, 7:34 a.m.
Created at: April 16, 2026, 2:58 p.m.