Triple

T538505
Position Surface form Disambiguated ID Type / Status
Subject Portuguese Ceylon E12377 entity
Predicate fortifications P1090 FINISHED
Object Jaffna Fort E13052 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: Jaffna Fort | Statement: [Portuguese Ceylon, fortifications, Jaffna Fort]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jaffna Fort
Context triple: [Portuguese Ceylon, fortifications, Jaffna Fort]
  • A. Jaffna chosen
    Jaffna is a historic city in northern Sri Lanka, known as a cultural and political center of Sri Lankan Tamils and for its strategic coastal location.
  • B. Trincomalee
    Trincomalee is a strategically important natural deep-water harbor and coastal city on the northeastern coast of Sri Lanka.
  • C. Batticaloa
    Batticaloa is a coastal city in eastern Sri Lanka known historically as an important regional port and trading center.
  • D. Bombay Castle
    Bombay Castle is a historic fortified complex in Mumbai that served as the core stronghold and early seat of British colonial administration in western India.
  • E. Amber Fort
    Amber Fort is a historic hilltop palace complex near Jaipur, India, renowned for its blend of Rajput and Mughal architecture and its richly decorated interiors.
  • 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_69a4933208e88190891f5debab1b776d completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a496dc0aac8190afb75ec6c47a1d2d completed March 1, 2026, 7:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4cc5aec388190861b0ee100790c7a completed March 1, 2026, 11:31 p.m.
Created at: March 1, 2026, 7:32 p.m.