Triple

T14630064
Position Surface form Disambiguated ID Type / Status
Subject Korah E343457 entity
Predicate hasSibling P363 FINISHED
Object Gatam E1109485 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: Gatam | Statement: [Korah, hasSibling, Gatam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gatam
Context triple: [Korah, hasSibling, Gatam]
  • A. Gatam chosen
    Gatam is a minor biblical figure mentioned in the Book of Genesis as a descendant within Esau’s family line.
  • B. Gamgadhi
    Gamgadhi is a remote town in northwestern Nepal that serves as an access point and administrative hub for the area around Rara National Park.
  • C. Ghatere
    Ghatere is a settlement located on the island of Kolombangara in the Solomon Islands.
  • D. Gharnāṭa
    Gharnāṭa is the historical Arabic name for the city of Granada in southern Spain, renowned as the last Muslim stronghold in the Iberian Peninsula and home to the Alhambra palace.
  • E. Ghatanji
    Ghatanji is a town in the Yavatmal district of Maharashtra, India, known for its local markets and surrounding agricultural region.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4a912248190a3df7f821395c776 completed April 14, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69fde16e85488190b0dcc2ccd2f5df4d completed May 8, 2026, 1:13 p.m.
Created at: April 10, 2026, 1:26 a.m.