Triple
T2329104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tulum |
E48359
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Tulum town |
E48359
|
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: Tulum town | Statement: [Tulum, hasPart, Tulum town]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tulum town Context triple: [Tulum, hasPart, Tulum town]
-
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.
Playa del Carmen, Mexico
Playa del Carmen, Mexico is a popular Caribbean coastal resort city on the Riviera Maya known for its beaches, tourism, and role as a venue for major regional and international events.
-
C.
Huatulco
Huatulco is a coastal resort town on Mexico’s Pacific coast, renowned for its nine picturesque bays, sandy beaches, and eco-friendly tourism.
-
D.
Puerto Escondido
Puerto Escondido is a coastal town and popular surfing and beach tourism destination on Mexico’s Pacific coast in the state of Oaxaca.
-
E.
Oxkintok
Oxkintok is an ancient Maya archaeological site in Mexico’s Yucatán Peninsula, notable for its early architecture and long history of occupation.
- 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_69a88aa308a88190b0b86c011fda7fce |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc665c6548190af90d70475b4519b |
completed | March 7, 2026, 6:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae96185a1c8190a115588f8a5b92f7 |
completed | March 9, 2026, 9:42 a.m. |
Created at: March 4, 2026, 7:50 p.m.