Triple

T21786673
Position Surface form Disambiguated ID Type / Status
Subject Mramorje necropolis at Rastište E537854 entity
Predicate locatedIn P40 FINISHED
Object Rastište
Rastište is a village in western Serbia known for its medieval Mramorje necropolis of stećak tombstones.
 E1503019 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: Rastište | Statement: [Mramorje necropolis at Rastište, locatedIn, Rastište]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rastište
Context triple: [Mramorje necropolis at Rastište, locatedIn, Rastište]
  • A. Pardais
    Pardais is a civil parish in the municipality of Vila Viçosa, in Portugal’s Alentejo region.
  • B. Rast
    Rast is a mutinous former member of the Night's Watch in Game of Thrones who participates in the betrayal at Craster's Keep and briefly helps hold it against Jon Snow's forces.
  • C. Ricadi
    Ricadi is a coastal town and municipality in the Calabria region of southern Italy, known for its scenic beaches and proximity to the popular tourist area of Capo Vaticano.
  • D. Raša
    Raša is a small town in Istria, Croatia, known as one of the youngest planned mining settlements in the region, built in the 1930s during Italian rule.
  • E. Tiba
    Tiba is a modern planned city in Egypt’s Luxor Governorate, developed to accommodate population growth and support regional economic and urban expansion.
  • 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: Rastište
Triple: [Mramorje necropolis at Rastište, locatedIn, Rastište]
Generated description
Rastište is a village in western Serbia known for its medieval Mramorje necropolis of stećak tombstones.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rastište
Target entity description: Rastište is a village in western Serbia known for its medieval Mramorje necropolis of stećak tombstones.
  • A. Pardais
    Pardais is a civil parish in the municipality of Vila Viçosa, in Portugal’s Alentejo region.
  • B. Rast
    Rast is a mutinous former member of the Night's Watch in Game of Thrones who participates in the betrayal at Craster's Keep and briefly helps hold it against Jon Snow's forces.
  • C. Ricadi
    Ricadi is a coastal town and municipality in the Calabria region of southern Italy, known for its scenic beaches and proximity to the popular tourist area of Capo Vaticano.
  • D. Raša
    Raša is a small town in Istria, Croatia, known as one of the youngest planned mining settlements in the region, built in the 1930s during Italian rule.
  • E. Tiba
    Tiba is a modern planned city in Egypt’s Luxor Governorate, developed to accommodate population growth and support regional economic and urban expansion.
  • 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_69e0c47198f881908cb0d237266c10e9 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0621b5d6881908b74bc999c94fa3d completed April 28, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a3e72ff48819092b5748718550120 completed May 17, 2026, 10:17 p.m.
NEDg Description generation batch_6a0a3fa18b8481909b0a0471bc4eb592 completed May 17, 2026, 10:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0a405450a0819089794cc07aa291b8 completed May 17, 2026, 10:25 p.m.
Created at: April 16, 2026, 6:52 p.m.