Triple

T7175841
Position Surface form Disambiguated ID Type / Status
Subject Maçka campus E167316 entity
Predicate locatedIn P40 FINISHED
Object Maçka, Istanbul
Maçka, Istanbul is a central neighborhood on the European side of Istanbul known for its parks, historic buildings, and university campuses.
E646554 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: Maçka, Istanbul | Statement: [Maçka campus, locatedIn, Maçka, Istanbul]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maçka, Istanbul
Context triple: [Maçka campus, locatedIn, Maçka, Istanbul]
  • A. Fatih, Istanbul
    Fatih is a historic central district of Istanbul known for its dense concentration of Ottoman-era architecture, religious institutions, and educational establishments.
  • B. Medinaceli
    Medinaceli is a historic town in the province of Soria, Spain, known for its well-preserved medieval architecture and Roman heritage.
  • C. Ortaköy
    Ortaköy is a lively Bosphorus-side neighborhood in Istanbul known for its waterfront mosque, cafes, and views of the Bosporus Bridge.
  • D. Beştepe
    Beştepe is a neighborhood in Ankara, Turkey, best known as the site of the Turkish Presidential Complex.
  • E. Brusa Bezistan
    Brusa Bezistan is a historic covered market building in Sarajevo’s old bazaar area, known for its Ottoman-era architecture and traditional trading stalls.
  • 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: Maçka, Istanbul
Triple: [Maçka campus, locatedIn, Maçka, Istanbul]
Generated description
Maçka, Istanbul is a central neighborhood on the European side of Istanbul known for its parks, historic buildings, and university campuses.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Maçka, Istanbul
Target entity description: Maçka, Istanbul is a central neighborhood on the European side of Istanbul known for its parks, historic buildings, and university campuses.
  • A. Fatih, Istanbul
    Fatih is a historic central district of Istanbul known for its dense concentration of Ottoman-era architecture, religious institutions, and educational establishments.
  • B. Medinaceli
    Medinaceli is a historic town in the province of Soria, Spain, known for its well-preserved medieval architecture and Roman heritage.
  • C. Ortaköy
    Ortaköy is a lively Bosphorus-side neighborhood in Istanbul known for its waterfront mosque, cafes, and views of the Bosporus Bridge.
  • D. Beştepe
    Beştepe is a neighborhood in Ankara, Turkey, best known as the site of the Turkish Presidential Complex.
  • E. Brusa Bezistan
    Brusa Bezistan is a historic covered market building in Sarajevo’s old bazaar area, known for its Ottoman-era architecture and traditional trading stalls.
  • 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_69c68889a2748190a316c5e65360361a completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e88ec6a8819083cbc3f4c39b8c79 completed March 27, 2026, 8:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7b9281e808190ac2a8ad585a70ea0 completed March 28, 2026, 11:19 a.m.
NEDg Description generation batch_69c7b9993f40819098c59865a3e64532 completed March 28, 2026, 11:20 a.m.
NED2 Entity disambiguation (via description) batch_69c7ba4f196c8190b29e6ddc091f11a6 completed March 28, 2026, 11:23 a.m.
Created at: March 27, 2026, 2:48 p.m.