Triple
T32531297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mixtecan |
E831461
|
entity |
| Predicate | partOfMacroFamily |
P89917
|
FINISHED |
| Object | Otomanguean |
—
|
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: Otomanguean | Statement: [Mixtecan, partOfMacroFamily, Otomanguean]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfMacroFamily Context triple: [Mixtecan, partOfMacroFamily, Otomanguean]
-
A.
macroFamily
Indicates that two or more language families are hypothesized to share a common higher-level genetic origin, forming a larger proposed macro-family grouping.
-
B.
belongsToMacrofamily
chosen
Indicates that a language is classified as part of a larger proposed language macrofamily.
-
C.
partOfType
Indicates that one entity represents a component, segment, or subset that belongs to or is included within the type or category represented by another entity.
-
D.
designedByFamilyOf
Indicates that something was created, planned, or conceived by one or more members of a particular family or familial group.
-
E.
catalogPartOf
Indicates that one catalog item is a component, section, or subset of a larger catalog or cataloged collection.
- 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_69f34924b1cc8190ad3aca0c0f012a7e |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ffb1218cb08190a814c7f0833501a7 |
completed | May 9, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69ffb083d6988190b2757e0cfd629b75 |
completed | May 9, 2026, 10:09 p.m. |
Created at: May 1, 2026, 1:01 a.m.