Triple
T23917961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kanjobal |
E602131
|
entity |
| Predicate | countryRegionDetail |
P94548
|
FINISHED |
| Object | southern Mexico |
—
|
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: southern Mexico | Statement: [Kanjobal, countryRegionDetail, southern Mexico]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryRegionDetail Context triple: [Kanjobal, countryRegionDetail, southern Mexico]
-
A.
countryRegion
Indicates that a country is located within, or belongs to, a specific geographic or administrative region.
-
B.
countryOrRegion
Indicates that one entity is a country or geographic region associated with another entity (such as its location, jurisdiction, or area of relevance).
-
C.
ISORegion
Indicates a standardized geographic or administrative region as defined by an ISO (International Organization for Standardization) code.
-
D.
countryEndpoint
Indicates a connection or interface that serves as the access point or boundary for interactions involving a specific country.
-
E.
regionDetail
chosen
Indicates a more specific or fine-grained subregion or localized area associated with a broader region.
- F. None of above.
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_69e2953a187081908346a9f36e85fc98 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cf153c6c819084aca5c13437fa3d |
completed | April 29, 2026, 9:27 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:40 p.m.