Triple

T21295140
Position Surface form Disambiguated ID Type / Status
Subject Puerto Aventuras E524900 entity
Predicate near P350 FINISHED
Object Tulum NE NERFINISHED

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: Tulum | Statement: [Puerto Aventuras, near, Tulum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tulum
Context triple: [Puerto Aventuras, near, Tulum]
  • A. Tulum chosen
    Tulum is a coastal town in Mexico’s Yucatán Peninsula best known for its well-preserved Mayan ruins perched on cliffs overlooking the Caribbean Sea and its popular beaches and resorts.
  • B. Tulum Valley
    Tulum Valley is a prominent viticultural and agricultural region in the province of San Juan, Argentina, known for its wine production and arid, sun-drenched landscape.
  • C. Akumal
    Akumal is a coastal town on Mexico’s Riviera Maya known for its tranquil beaches, coral reefs, and sea turtle snorkeling.
  • D. Cancuén
    Cancuén is a major ancient Maya archaeological site in Guatemala known for its large palace complex and role as a key trade center.
  • E. Puerto Morelos
    Puerto Morelos is a laid-back coastal town on Mexico’s Caribbean coast known for its tranquil beaches, coral reef snorkeling, and more relaxed atmosphere than larger Riviera Maya resorts.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b517e6748190850d6f6ddf323d69 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73857784881908c3b8418a4c00c1e completed April 21, 2026, 8:41 a.m.
Created at: April 16, 2026, 4:04 p.m.