Triple

T9240179
Position Surface form Disambiguated ID Type / Status
Subject Sultan Husayn E222036 entity
Predicate courtCity P3207 FINISHED
Object Isfahan E68692 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: Isfahan | Statement: [Sultan Husayn, courtCity, Isfahan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isfahan
Context triple: [Sultan Husayn, courtCity, Isfahan]
  • A. Isfahan chosen
    Isfahan is a historic Iranian city renowned for its Safavid-era architecture, grand mosques, and role as a major political and cultural center in early modern Persia.
  • B. Mashhad
    Mashhad is a major city in northeastern Iran renowned as a leading religious and cultural center of the Islamic world, centered around the shrine of Imam Reza.
  • C. شیراز
    شیراز یکی از مهم‌ترین و تاریخی‌ترین شهرهای ایران است که به‌عنوان مرکز فرهنگ، ادب و شعر فارسی شناخته می‌شود.
  • D. Kashan
    Kashan is an Iranian city renowned for its rich history, traditional architecture, and production of high-quality Persian carpets.
  • E. Hamadan
    Hamadan is an ancient city in western Iran, historically significant as a major center of Persian Jewish life and one of the oldest continuously inhabited cities in the region.
  • 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: courtCity
Context triple: [Sultan Husayn, courtCity, Isfahan]
  • A. city1
    Indicates that the subject is classified as a city.
  • B. city2 chosen
    Indicates a relationship where one entity is identified as a city associated with, located in, or otherwise linked to another entity.
  • C. cityName
    Indicates that the associated value is the name of a city.
  • D. principalCityOf
    Indicates that a city serves as the main or most important city (often administrative, economic, or cultural center) of a specified region or area.
  • E. jurisdictionCity
    Indicates that a city has legal or administrative authority over, or is the governing jurisdiction for, a given entity or matter.
  • 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_69ca83ee26cc81909ac624e190597d6d completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccf0a3888c8190b72d8d0b850bdfbc completed April 1, 2026, 10:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d89eedc66c81909076cc7ba35f9da5 completed April 10, 2026, 6:55 a.m.
PD Predicate disambiguation batch_69cc7a4765648190aa9445c4a22dc471 completed April 1, 2026, 1:52 a.m.
Created at: March 30, 2026, 7:30 p.m.