Triple

T15314784
Position Surface form Disambiguated ID Type / Status
Subject Old Kandahar archaeological site E366126 entity
Predicate partOf P40 FINISHED
Object Arachosia E366125 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: Arachosia | Statement: [Old Kandahar archaeological site, partOf, Arachosia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arachosia
Context triple: [Old Kandahar archaeological site, partOf, Arachosia]
  • A. Arachosia chosen
    Arachosia was an ancient historical region in south-central Asia, roughly corresponding to parts of modern southern Afghanistan and Pakistan, known as a crossroads of Persian, Greek, and later empires.
  • B. Drangiana
    Drangiana was an ancient historical region in southwestern Afghanistan and eastern Iran, known from Achaemenid and later classical sources.
  • C. Kharas
    Kharas is a Palestinian village located in the Hebron Governorate in the southern West Bank.
  • D. Araḫsamna
    Araḫsamna is a month in the ancient Babylonian calendar, corresponding roughly to a late autumn period in the Mesopotamian year.
  • E. Gharsana
    Gharsana is a town in the arid northwestern region of Rajasthan, India, known for its agriculture supported by canal irrigation and its proximity to the India–Pakistan border.
  • 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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03dd050108190a584543cb93943a4 completed April 16, 2026, 1:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff1a6582908190a9a56652e9ccc5a1 completed May 9, 2026, 11:28 a.m.
Created at: April 10, 2026, 3:16 a.m.