Triple

T7991777
Position Surface form Disambiguated ID Type / Status
Subject Shuja-ud-Daula E186024 entity
Predicate capital P234 FINISHED
Object Faizabad E64151 NE FINISHED

How this triple was built (2 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: Faizabad | Statement: [Shuja-ud-Daula, capital, Faizabad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Faizabad
Context triple: [Shuja-ud-Daula, capital, Faizabad]
  • A. Faizabad chosen
    Faizabad is a historic city in the Indian state of Uttar Pradesh that once served as the capital of the former princely state of Oudh (Awadh).
  • B. Khuldabad
    Khuldabad is a historic town in Maharashtra, India, renowned as the burial site of the Mughal emperor Aurangzeb and several prominent Sufi saints.
  • C. Moradabad
    Moradabad is a major city in northern India known for its brass handicraft industry and is located in the state of Uttar Pradesh.
  • D. Ferozabad
    Ferozabad is a residential and commercial neighborhood located within the Karachi East District of Karachi, Pakistan.
  • E. Ghazipur
    Ghazipur is a city in the Indian state of Uttar Pradesh, known for its historical significance and as a regional hub in eastern Uttar Pradesh.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca829c6c308190ab05b43d234c52b2 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3c712d0481908d163d2509d054fa completed March 31, 2026, 3:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc568393008190b8ff6cc17f9b5c46 completed March 31, 2026, 11:19 p.m.
Created at: March 30, 2026, 5:16 p.m.