Triple

T12310117
Position Surface form Disambiguated ID Type / Status
Subject Pune district E293453 entity
Predicate hasFort P3479 FINISHED
Object Torna Fort E939279 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: Torna Fort | Statement: [Pune district, hasFort, Torna Fort]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Torna Fort
Context triple: [Pune district, hasFort, Torna Fort]
  • A. Torna Fort chosen
    Torna Fort is a historic hill fort in Maharashtra, India, renowned as the first major fort captured and restored by Chhatrapati Shivaji Maharaj, marking the foundation of the Maratha Hindavi Swarajya.
  • B. Fortress
    A fortress is a heavily fortified defensive structure, often with thick walls, towers, and battlements, built to protect people and strategic locations from attack.
  • C. Toma
    Toma is a traditional semi-hard cow’s milk cheese from Italy’s Piedmont region, known for its mild, buttery flavor and smooth, elastic texture.
  • D. Toma
    Toma is a major Mande language spoken primarily in Guinea and neighboring West African countries.
  • E. Forte
    Forte is an Italian surname borne by various notable individuals in fields such as religion, arts, and sports.
  • 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_69d6ab6a2b50819082f6aedd32ed608a completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f02c0508190b10c0627cdaaba76 completed April 10, 2026, 6:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69f61e84fa708190854afc6afd425fd7 completed May 2, 2026, 3:55 p.m.
Created at: April 8, 2026, 9:53 p.m.