Triple

T5997864
Position Surface form Disambiguated ID Type / Status
Subject Belgrade Fortress E133517 entity
Predicate hasPart P35 FINISHED
Object Barutana
Barutana is a historic gunpowder storage complex within Belgrade Fortress, now often used as a cultural and event space.
 E560487 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: Barutana | Statement: [Belgrade Fortress, hasPart, Barutana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Barutana
Context triple: [Belgrade Fortress, hasPart, Barutana]
  • A. Bara
    Bara is a town in Pakistan’s Khyber District, known as a key settlement in the Khyber Pass region with strategic and commercial significance.
  • B. Barara
    Barara is a town in the Ambala district of the northern Indian state of Haryana, known primarily as a local administrative and market center for surrounding rural areas.
  • C. Boroko
    Boroko is a major residential and commercial suburb of Port Moresby in Papua New Guinea, known for its shopping areas and sports facilities.
  • D. Barisakho
    Barisakho is a small mountain village in the historic Khevsureti region of northeastern Georgia, serving as one of its local centers.
  • E. Tzununá
    Tzununá is a small, tranquil Mayan village in Guatemala known for its natural beauty, traditional culture, and growing community of eco-lodges and retreat centers.
  • 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: Barutana
Triple: [Belgrade Fortress, hasPart, Barutana]
Generated description
Barutana is a historic gunpowder storage complex within Belgrade Fortress, now often used as a cultural and event space.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Barutana
Target entity description: Barutana is a historic gunpowder storage complex within Belgrade Fortress, now often used as a cultural and event space.
  • A. Bara
    Bara is a town in Pakistan’s Khyber District, known as a key settlement in the Khyber Pass region with strategic and commercial significance.
  • B. Barara
    Barara is a town in the Ambala district of the northern Indian state of Haryana, known primarily as a local administrative and market center for surrounding rural areas.
  • C. Boroko
    Boroko is a major residential and commercial suburb of Port Moresby in Papua New Guinea, known for its shopping areas and sports facilities.
  • D. Barisakho
    Barisakho is a small mountain village in the historic Khevsureti region of northeastern Georgia, serving as one of its local centers.
  • E. Tzununá
    Tzununá is a small, tranquil Mayan village in Guatemala known for its natural beauty, traditional culture, and growing community of eco-lodges and retreat centers.
  • 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_69c00870ddbc81909880fa3864f4f38d completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04ee274e08190b6478c7ae318ae48 completed March 22, 2026, 8:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1087d08f081909842940a28bddb35 completed March 23, 2026, 9:31 a.m.
NEDg Description generation batch_69c1094d6d408190abde0d2e582c15a5 completed March 23, 2026, 9:35 a.m.
NED2 Entity disambiguation (via description) batch_69c109c333208190b90911e0cab58377 completed March 23, 2026, 9:37 a.m.
Created at: March 22, 2026, 4:05 p.m.