Triple
T6927466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sipakapense |
E160347
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Akatek |
E166217
|
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: Akatek | Statement: [Sipakapense, closelyRelatedTo, Akatek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Akatek Context triple: [Sipakapense, closelyRelatedTo, Akatek]
-
A.
Akatek
chosen
Akatek is a Mayan language spoken primarily by indigenous communities in the highlands of Guatemala.
-
B.
Acolhua
The Acolhua were a Nahua-speaking Mesoamerican people of central Mexico, closely allied with the Aztecs and centered in the city-state of Texcoco.
-
C.
Ixcatec
Ixcatec is an indigenous Oto-Manguean language of Mexico spoken by a very small and endangered community in Oaxaca.
-
D.
Tepanec
The Tepanec were a powerful Nahua-speaking people of central Mexico who dominated the Valley of Mexico before being defeated by the Aztec-led Triple Alliance in the 15th century.
-
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_69c6884d350081908d8a970e4d40ad78 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6da1bf2088190a8ccfa01d9a1efc5 |
completed | March 27, 2026, 7:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c769fa17748190a1ca72ca86cce827 |
completed | March 28, 2026, 5:41 a.m. |
Created at: March 27, 2026, 2:27 p.m.