Triple

T10547167
Position Surface form Disambiguated ID Type / Status
Subject Saba E248850 entity
Predicate majorDeity P7648 FINISHED
Object Almaqah E658555 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: Almaqah | Statement: [Saba, majorDeity, Almaqah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Almaqah
Context triple: [Saba, majorDeity, Almaqah]
  • A. Almaqah chosen
    Almaqah is the principal moon god of the ancient Sabaean civilization in South Arabia, associated with kingship, fertility, and monumental temple complexes.
  • B. Ta’if
    Ta’if is a historic city in western Saudi Arabia, situated in the mountains near Mecca and known for its cool climate, agriculture, and role in early Islamic history.
  • C. Khujayli
    Khujayli is a city in the autonomous Republic of Karakalpakstan in western Uzbekistan, serving as one of its local administrative and population centers.
  • D. Qardaha
    Qardaha is a town in northwestern Syria best known as the ancestral home of the Assad family, which has dominated the country’s political leadership for decades.
  • E. Al Khurmah
    Al Khurmah is a town in western Saudi Arabia situated within the Makkah Province.
  • 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_69d381c733c08190ab1dd6239f5f34ae completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d526d20ef48190ab9f70d4ce5f2a11 completed April 7, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69d96b474a248190b46c31e8e0008f9f completed April 10, 2026, 9:27 p.m.
Created at: April 6, 2026, 12:33 p.m.