Triple
T6561612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Itzaʼ |
E153795
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Lacandon |
E157527
|
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: Lacandon | Statement: [Itzaʼ, closelyRelatedTo, Lacandon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lacandon Context triple: [Itzaʼ, closelyRelatedTo, Lacandon]
-
A.
Lacandon
chosen
Lacandon is a Mayan language spoken by the Lacandon people of the Lacandon Jungle in Chiapas, Mexico, known for preserving many archaic features of the Mayan language family.
-
B.
Pemón
Pemón is an indigenous people of the Gran Sabana region in southeastern Venezuela, known for their distinct language and close relationship with the Canaima National Park area.
-
C.
Popoluca
Popoluca refers to several closely related indigenous languages of the Mixe–Zoquean family spoken by native communities in southern Veracruz, Mexico.
-
D.
Mazatec
Mazatec is an indigenous Oto-Manguean language (or group of closely related languages) spoken primarily by the Mazatec people in the Mexican states of Oaxaca, Puebla, and Veracruz.
-
E.
Huastec
Huastec is a Mayan language spoken by the Huastec people primarily in northeastern Mexico, especially in parts of Veracruz and neighboring states.
- 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_69c6880cb35881909b763eb0125236b9 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ae37a5b0819091692fc5def270b9 |
completed | March 27, 2026, 4:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6e42523848190b02682e6a640ac05 |
completed | March 27, 2026, 8:10 p.m. |
Created at: March 27, 2026, 1:52 p.m.