Triple

T8556008
Position Surface form Disambiguated ID Type / Status
Subject Angelus Novus E202564 entity
Predicate location P40 FINISHED
Object Jerusalem E6995 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: Jerusalem | Statement: [Angelus Novus, location, Jerusalem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jerusalem
Context triple: [Angelus Novus, location, Jerusalem]
  • A. Jerusalem chosen
    Jerusalem is an ancient and historically significant city in the Middle East that serves as a major religious and cultural center for Judaism, Christianity, and Islam.
  • B. Jerusalem
    Jerusalem is a novel by Swedish author Selma Lagerlöf that portrays the lives, faith, and emigration of a group of Swedish villagers who journey to the Holy Land.
  • C. Jesusalém
    Jesusalém is a novel by Mozambican writer Mia Couto that explores memory, war, and identity through a boy’s life in an isolated, post-conflict African landscape.
  • D. Jerusalem city center
    Jerusalem city center is the main commercial and cultural hub of Jerusalem, featuring busy shopping streets, historic sites, and key public institutions.
  • E. West Jerusalem
    West Jerusalem is the predominantly Jewish, modern western sector of Jerusalem that has served as the seat of Israel’s government institutions since 1949.
  • 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_69ca832610e08190b3b6c6cd2c250255 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe88bcce081909e12e4037a0e6323 completed March 31, 2026, 3:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce893b24c0819094fead15749fe1ee completed April 2, 2026, 3:20 p.m.
Created at: March 30, 2026, 6:19 p.m.