Triple

T22718888
Position Surface form Disambiguated ID Type / Status
Subject Esagila tablet E561806 entity
Predicate religiousSiteDescribed P34373 FINISHED
Object main temple of Marduk in Babylon LITERAL 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: main temple of Marduk in Babylon | Statement: [Esagila tablet, religiousSiteDescribed, main temple of Marduk in Babylon]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: religiousSiteDescribed
Context triple: [Esagila tablet, religiousSiteDescribed, main temple of Marduk in Babylon]
  • A. religiousSiteType chosen
    Indicates the specific kind or category of religious site associated with an entity (e.g., church, mosque, temple).
  • B. religiousSiteRank
    Indicates the hierarchical or status-based rank assigned to a religious site within a religious or organizational structure.
  • C. isPlaceOfPilgrimageFor
    Indicates that a location serves as a destination for religious or spiritual pilgrimage for a person or group.
  • D. nearReligiousSite
    Indicates that one entity is located close to or in the immediate vicinity of a religious site.
  • E. religiousSiteAffected
    Indicates that a religious site is impacted or influenced by a particular event, action, or condition.
  • F. None of above.

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_69e2454fc984819088213b58ee87a002 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1790fbf9c819082ba7b48801a7b39 completed April 29, 2026, 3:20 a.m.
PD Predicate disambiguation batch_69eed2a971c0819088af574e40c9343f completed April 27, 2026, 3:06 a.m.
Created at: April 17, 2026, 3:19 p.m.