Triple

T3670080
Position Surface form Disambiguated ID Type / Status
Subject Amarna letters E77856 entity
Predicate includesCorrespondenceWith P16605 FINISHED
Object Hatti E203755 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: Hatti | Statement: [Amarna letters, includesCorrespondenceWith, Hatti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hatti
Context triple: [Amarna letters, includesCorrespondenceWith, Hatti]
  • A. Hatti chosen
    Hatti was an ancient Anatolian kingdom and cultural region centered in central Turkey, later absorbed into the Hittite Empire.
  • B. Kaneš
    Kaneš was an important ancient Anatolian city, known as a major Assyrian trading colony and archaeological site in central Turkey.
  • C. Avaris
    Avaris was the ancient Hyksos capital in the Nile Delta of Egypt, known as a major political and religious center during the Second Intermediate Period.
  • D. Kalhu
    Kalhu, also known as Nimrud, was a prominent ancient Assyrian city that served as a royal capital and major administrative and cultural center of the Neo-Assyrian Empire.
  • E. Ugarit
    Ugarit was an important ancient port city-state on the Syrian coast, known for its influential Canaanite culture and the discovery of one of the earliest alphabetic writing systems.
  • 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_69ad85e083008190b2e1b7085fe500bd completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc42b3f94819091d51e488bc3f2f2 completed March 8, 2026, 6:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b48850515c8190bdb9ddcfc0a13f4e completed March 13, 2026, 9:57 p.m.
Created at: March 8, 2026, 3:25 p.m.