Triple

T3905499
Position Surface form Disambiguated ID Type / Status
Subject Al-Attarine Madrasa E87194 entity
Predicate locatedIn P40 FINISHED
Object Fez E12903 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: Fez | Statement: [Al-Attarine Madrasa, locatedIn, Fez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fez
Context triple: [Al-Attarine Madrasa, locatedIn, Fez]
  • A. Fez chosen
    Fez is a historic imperial city in northern Morocco renowned for its well-preserved medieval medina, traditional craftsmanship, and status as a major cultural and religious center.
  • B. Zakros
    Zakros is an important Minoan archaeological site on the eastern coast of Crete, known for the remains of a palace complex and its role in Bronze Age trade.
  • C. Sollum
    Sollum is a small coastal town in northwestern Egypt near the Libyan border that has historically served as a strategic military and trading point, particularly during World War II.
  • D. Battir
    Battir is a Palestinian village near Bethlehem renowned for its ancient terraced agriculture and irrigation system, recognized as a UNESCO World Heritage Site.
  • E. Carcassonne
    Carcassonne is a historic fortified city in southern France renowned for its medieval citadel with double walls and numerous watchtowers.
  • 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_69aed9424514819086e9c58adde6652d completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeed1102b08190a9f5087ff9be0358 completed March 9, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b55614ffa48190b15a1c2ec20638f2 completed March 14, 2026, 12:35 p.m.
Created at: March 9, 2026, 3:22 p.m.