Triple

T23058148
Position Surface form Disambiguated ID Type / Status
Subject Province of Zara E574218 entity
Predicate capital P234 FINISHED
Object Zara
Zara is a historic coastal city on the Adriatic Sea, now known as Zadar in Croatia, noted for its Roman and medieval architecture and rich maritime heritage.
 E137996 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: Zara | Statement: [Province of Zara, capital, Zara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zara
Context triple: [Province of Zara, capital, Zara]
  • A. Zara
    Zara is a global fast-fashion retail brand known for rapidly translating runway trends into affordable clothing and accessories for a mass-market audience.
  • B. Zara
    Zara is a town and district in Turkey known for its location in the eastern part of the Central Anatolia region.
  • C. Zara
    Zara is a British equestrian and member of the royal family, known as the daughter of Princess Anne and granddaughter of Queen Elizabeth II.
  • D. Zara
    "Zara" is a 1732 tragedy play by Aaron Hill, adapted from Voltaire's "Zaïre" and notable in early 18th-century English theatre.
  • E. Zara
    "Zara" is a 1736 tragedy play by Aaron Hill, adapted from Voltaire’s "Zaïre" and notable in 18th-century English theatre.
  • 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: Zara
Triple: [Province of Zara, capital, Zara]
Generated description
Zara is a historic coastal city on the Adriatic Sea, now known as Zadar in Croatia, noted for its Roman and medieval architecture and rich maritime heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zara
Target entity description: Zara is a historic coastal city on the Adriatic Sea, now known as Zadar in Croatia, noted for its Roman and medieval architecture and rich maritime heritage.
  • A. Zara chosen
    Zara is the historical Italian name for the coastal Croatian city of Zadar on the Adriatic Sea.
  • B. Zara
    Zara is a town and district in Turkey known for its location in the eastern part of the Central Anatolia region.
  • C. Zara
    Zara is a station on Milan’s Metro Line 3, serving as a public transportation stop within the city’s underground network.
  • D. Zara
    Zara is a global fast-fashion retail brand known for rapidly translating runway trends into affordable clothing and accessories for a mass-market audience.
  • E. Zara
    Zara is a British equestrian and member of the royal family, known as the daughter of Princess Anne and granddaughter of Queen Elizabeth II.
  • F. None of above.

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_69e245ba7ae48190be606dbc54120e39 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18681bec48190a8226b3d89d19b9f completed April 29, 2026, 4:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c0ae4657c8190bf4d211e68e8cfa7 completed May 19, 2026, 7:01 a.m.
NEDg Description generation batch_6a0c0b8e7ca48190ae8a6a97221cc671 completed May 19, 2026, 7:04 a.m.
NED2 Entity disambiguation (via description) batch_6a0c0c10edd08190b1a270bff6ca80c2 completed May 19, 2026, 7:06 a.m.
Created at: April 17, 2026, 3:55 p.m.