Triple

T11801947
Position Surface form Disambiguated ID Type / Status
Subject Kabah E280647 entity
Predicate connectedTo P37 FINISHED
Object Uxmal E47862 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: Uxmal | Statement: [Kabah, connectedTo, Uxmal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uxmal
Context triple: [Kabah, connectedTo, Uxmal]
  • A. Uxmal chosen
    Uxmal is a major ancient Maya city in present-day Mexico, renowned for its well-preserved Puuc-style architecture and impressive pyramids and palaces.
  • B. Pangkal Balam
    Pangkal Balam is a port town on Bangka Island in Indonesia that serves as an important hub for regional maritime transport and trade.
  • C. San Luis de Palenque
    San Luis de Palenque is a rural municipality in eastern Colombia known for its cattle ranching, llanero (plains) culture, and location within the Orinoquía region.
  • D. Izamal
    Izamal is a historic colonial town in Mexico’s Yucatán Peninsula, known for its striking yellow-painted buildings and important Mayan archaeological sites.
  • E. Palenque
    Palenque is an ancient Maya city in modern-day Chiapas, Mexico, renowned for its well-preserved temples, palaces, and intricate inscriptions.
  • 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_69d6ab258b808190b1735835c841e3a4 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a5a4512c8190b7782e1dee053000 completed April 10, 2026, 7:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69f166dbcb848190a5942ec00a2ca2f9 completed April 29, 2026, 2:03 a.m.
Created at: April 8, 2026, 9:42 p.m.