Triple

T8448711
Position Surface form Disambiguated ID Type / Status
Subject Serdica E199745 entity
Predicate modernRemainsLocatedIn P33372 FINISHED
Object Largo of Sofia E641782 NE FINISHED

How this triple was built (3 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: Largo of Sofia | Statement: [Serdica, modernRemainsLocatedIn, Largo of Sofia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Largo of Sofia
Context triple: [Serdica, modernRemainsLocatedIn, Largo of Sofia]
  • A. Largo of Sofia chosen
    The Largo of Sofia is a central architectural ensemble and public square in Bulgaria’s capital, known for its monumental socialist-era buildings and role as a key civic and governmental hub.
  • B. Boyana, Sofia
    Boyana, Sofia is a prestigious residential neighborhood at the foot of Vitosha Mountain in Sofia, Bulgaria, known for its natural scenery, affluent homes, and cultural landmarks.
  • C. Ovcha Kupel, Sofia
    Ovcha Kupel is a residential district in western Sofia, Bulgaria, known for hosting the home stadium of football club PFC Slavia Sofia.
  • D. Kantemirovskaya
    Kantemirovskaya is a Moscow Metro station serving the Zamoskvoretskaya Line in the southern part of the city.
  • E. Landa
    Landa is a writing system historically used in parts of the Indian subcontinent, particularly in the Punjab region, for commercial and administrative purposes.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: modernRemainsLocatedIn
Context triple: [Serdica, modernRemainsLocatedIn, Largo of Sofia]
  • A. culturalRemains
    Indicates that one entity consists of or contains physical or material traces left by a culture, such as artifacts, structures, or other archaeological evidence.
  • B. housesRemainsOf chosen
    Indicates that one entity serves as the location or container in which the physical remains of another entity are kept or preserved.
  • C. relicsLocatedIn
    Indicates that certain relics are situated, stored, or found within a specific location.
  • D. excavatedAt
    Indicates that an excavation activity took place at a specific location or site.
  • E. excavatedIn
    Indicates that something (typically an artifact, structure, or site) was uncovered or dug out during an excavation that took place at a specific time or within a specific time period.
  • F. None of above.

Provenance (4 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_69ca83170f9081909cd98f55614c6476 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe445b7988190b53ae45070c70d1d completed March 31, 2026, 3:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce1dbf2e2c8190b20e842438acb4d5 completed April 2, 2026, 7:41 a.m.
PD Predicate disambiguation batch_69cbd0f5a3648190beb53a139a2d5482 completed March 31, 2026, 1:49 p.m.
Created at: March 30, 2026, 6:09 p.m.