Triple
T10349038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Macanxoc |
E243830
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Cobá |
E49046
|
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: Cobá | Statement: [Lake Macanxoc, adjacentTo, Cobá]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cobá Context triple: [Lake Macanxoc, adjacentTo, Cobá]
-
A.
Cobá
chosen
Cobá is an ancient Maya city in Mexico’s Yucatán Peninsula, known for its extensive network of sacbeob (raised stone roads) and towering pyramid structures amid dense jungle.
-
B.
Comalcalco
Comalcalco is a city in the Mexican state of Tabasco known for its nearby Maya archaeological site built with brick structures.
-
C.
Nojpetén
Nojpetén was the last independent Maya capital city, located on an island in Lake Petén Itzá in present-day Guatemala.
-
D.
Coacalco
Coacalco is a suburban municipality in the State of Mexico that forms part of the greater Mexico City metropolitan area.
-
E.
Xilitla
Xilitla is a picturesque town in the Huasteca region of San Luis Potosí, Mexico, known for its lush mountainous landscape and its association with surrealist art and architecture.
- 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_69d381b22b8c8190aaed476be5f872a9 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e946cbb881909b88536d0107995d |
completed | April 7, 2026, 11:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d979ecfef48190a6014601bcddf761 |
completed | April 10, 2026, 10:30 p.m. |
Created at: April 6, 2026, 11:57 a.m.