Triple

T2070199
Position Surface form Disambiguated ID Type / Status
Subject Janica Kostelić E44798 entity
Predicate familyName P18 FINISHED
Object Kostelić
Kostelić is a Croatian surname most famously associated with the champion alpine skiing family that includes Olympic gold medalist Janica Kostelić.
 E230995 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: Kostelić | Statement: [Janica Kostelić, familyName, Kostelić]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kostelić
Context triple: [Janica Kostelić, familyName, Kostelić]
  • A. Ružić
    Ružić is a South Slavic surname of Croatian and Serbian origin borne by various notable individuals.
  • B. Mihajlo
    Mihajlo is the Serbian given name of Michael I. Pupin, the renowned Serbian-American physicist, inventor, and Columbia University professor.
  • C. Tomislav Tomašević
    Tomislav Tomašević is a Croatian politician and environmental activist who serves as the mayor of Zagreb and is a leading figure of the green-left political movement in Croatia.
  • D. Dragaš
    Dragaš is a Serbian medieval noble family name most notably borne by Helena Dragaš, the Byzantine empress and mother of the last Byzantine emperor, Constantine XI Palaiologos.
  • E. Saša
    Saša is a given name commonly used in Slavic countries, often as a diminutive of Aleksandar or Aleksandra.
  • 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: Kostelić
Triple: [Janica Kostelić, familyName, Kostelić]
Generated description
Kostelić is a Croatian surname most famously associated with the champion alpine skiing family that includes Olympic gold medalist Janica Kostelić.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kostelić
Target entity description: Kostelić is a Croatian surname most famously associated with the champion alpine skiing family that includes Olympic gold medalist Janica Kostelić.
  • A. Ružić
    Ružić is a South Slavic surname of Croatian and Serbian origin borne by various notable individuals.
  • B. Mihajlo
    Mihajlo is the Serbian given name of Michael I. Pupin, the renowned Serbian-American physicist, inventor, and Columbia University professor.
  • C. Tomislav Tomašević
    Tomislav Tomašević is a Croatian politician and environmental activist who serves as the mayor of Zagreb and is a leading figure of the green-left political movement in Croatia.
  • D. Dragaš
    Dragaš is a Serbian medieval noble family name most notably borne by Helena Dragaš, the Byzantine empress and mother of the last Byzantine emperor, Constantine XI Palaiologos.
  • E. Saša
    Saša is a given name commonly used in Slavic countries, often as a diminutive of Aleksandar or Aleksandra.
  • 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_69a88916c2b48190a5ca2e9b12cad3ed completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb9f677108190aea3c8db7850c892 completed March 7, 2026, 5:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae27289eb081909bfbc9bf2cd14878 completed March 9, 2026, 1:49 a.m.
NEDg Description generation batch_69ae28c163088190818891302f7faa8e completed March 9, 2026, 1:56 a.m.
NED2 Entity disambiguation (via description) batch_69ae292a9d7481909acbc3a5f24ff0b9 completed March 9, 2026, 1:58 a.m.
Created at: March 4, 2026, 7:41 p.m.