Triple

T14468686
Position Surface form Disambiguated ID Type / Status
Subject Qara Khitai E358780 entity
Predicate capital P234 FINISHED
Object Balasagun E660675 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: Balasagun | Statement: [Qara Khitai, capital, Balasagun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Balasagun
Context triple: [Qara Khitai, capital, Balasagun]
  • A. Balasagun chosen
    Balasagun was a prominent medieval Central Asian city in the Chüy Valley, historically significant as a political and cultural center along the Silk Road.
  • B. Guzamala
    Guzamala is a local government area in Borno State, northeastern Nigeria, known for its rural communities and location within the Lake Chad region.
  • C. Teneguía
    Teneguía is a volcanic cone on the island of La Palma in Spain’s Canary Islands, known for its dramatic 1971 eruption.
  • D. Toramana
    Toramana was a prominent Huna ruler in early 6th-century northern India, known for his extensive military campaigns and significant role in weakening the Gupta Empire.
  • E. Guindulungan
    Guindulungan is a municipality in the province of Maguindanao in the Bangsamoro Autonomous Region in Muslim Mindanao in the southern Philippines.
  • 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_69d827966698819082e140837737501d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de91f8613c819080424104c0b7f4c3 completed April 14, 2026, 7:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd649beec88190861abb52c5a2733e completed May 8, 2026, 4:20 a.m.
Created at: April 10, 2026, 1:20 a.m.