Triple

T22480848
Position Surface form Disambiguated ID Type / Status
Subject Umm el-Qaab necropolis E555758 entity
Predicate hasPart P35 FINISHED
Object Cemetery B NE NERFINISHED

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: Cemetery B | Statement: [Umm el-Qaab necropolis, hasPart, Cemetery B]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cemetery B
Context triple: [Umm el-Qaab necropolis, hasPart, Cemetery B]
  • A. Cemetery B chosen
    Cemetery B is an early dynastic royal burial ground at Umm el-Qaab in Abydos, Egypt, associated with some of the first pharaohs.
  • B. Benge Cemetery
    Benge Cemetery is a small rural burial ground serving the community of Benge in Adams County, Washington.
  • C. Ballana cemetery
    Ballana cemetery is an archaeological burial site in Lower Nubia notable for its rich royal tombs and artifacts from the late Meroitic and post-Meroitic periods.
  • D. Jellaz Cemetery
    Jellaz Cemetery is a historic and prominent Muslim burial ground in Tunis, Tunisia, known as the resting place of many notable Tunisian figures.
  • E. Mamilla Cemetery
    Mamilla Cemetery is an ancient Islamic burial ground in Jerusalem, historically significant for its centuries-old tombs and its location near the Old City.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e53897c819088863779f8c50bb0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15c397b248190b36c2fbfa6489693 completed April 29, 2026, 1:17 a.m.
Created at: April 16, 2026, 8:49 p.m.