Triple

T16127014
Position Surface form Disambiguated ID Type / Status
Subject Medjugorje E391297 entity
Predicate titleOfMary P103067 FINISHED
Object Gospa
Gospa is a local Croatian term affectionately used for the Virgin Mary, particularly associated with reported Marian apparitions in Medjugorje.
 E1196346 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: Gospa | Statement: [Medjugorje, titleOfMary, Gospa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gospa
Context triple: [Medjugorje, titleOfMary, Gospa]
  • A. Bogorodica
    Bogorodica is a small settlement in the Gevgelija region of southeastern North Macedonia, known for its proximity to the Greek border and its role as a local transit point.
  • B. Krestena
    Krestena is a small town in western Greece, located in the regional unit of Elis in the Peloponnese.
  • C. Goče
    Goče is a small, historic village in western Slovenia known for its traditional stone architecture and winegrowing heritage within the Vipava Valley.
  • D. Popa
    Popa is a town located in Ogooué-Lolo Province in central-eastern Gabon.
  • E. Our Lady of Ljeviš
    Our Lady of Ljeviš is a medieval Serbian Orthodox church in Prizren, Kosovo, renowned for its 14th-century frescoes and status as a UNESCO World Heritage Site.
  • 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: Gospa
Triple: [Medjugorje, titleOfMary, Gospa]
Generated description
Gospa is a local Croatian term affectionately used for the Virgin Mary, particularly associated with reported Marian apparitions in Medjugorje.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gospa
Target entity description: Gospa is a local Croatian term affectionately used for the Virgin Mary, particularly associated with reported Marian apparitions in Medjugorje.
  • A. Bogorodica
    Bogorodica is a small settlement in the Gevgelija region of southeastern North Macedonia, known for its proximity to the Greek border and its role as a local transit point.
  • B. Krestena
    Krestena is a small town in western Greece, located in the regional unit of Elis in the Peloponnese.
  • C. Goče
    Goče is a small, historic village in western Slovenia known for its traditional stone architecture and winegrowing heritage within the Vipava Valley.
  • D. Popa
    Popa is a town located in Ogooué-Lolo Province in central-eastern Gabon.
  • E. Our Lady of Ljeviš
    Our Lady of Ljeviš is a medieval Serbian Orthodox church in Prizren, Kosovo, renowned for its 14th-century frescoes and status as a UNESCO World Heritage Site.
  • 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_69d87f1bb0988190b490d273dbf3fd03 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21a02172c8190978f7951ccd80928 completed April 17, 2026, 11:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff2abf9b08190a375abc842a0e7d0 completed May 10, 2026, 2:51 a.m.
NEDg Description generation batch_69fff35ded288190b4d261358f1661cb completed May 10, 2026, 2:54 a.m.
NED2 Entity disambiguation (via description) batch_69fff3f2760c8190a58fedc2798614ae completed May 10, 2026, 2:56 a.m.
Created at: April 10, 2026, 5 a.m.