Triple
T6932309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mesoamerican Long Count calendar |
E160464
|
entity |
| Predicate | unitLength |
P12631
|
FINISHED |
| Object | 1 winal = 20 kʼin = 20 days |
—
|
LITERAL 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: 1 winal = 20 kʼin = 20 days | Statement: [Mesoamerican Long Count calendar, unitLength, 1 winal = 20 kʼin = 20 days]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unitLength Context triple: [Mesoamerican Long Count calendar, unitLength, 1 winal = 20 kʼin = 20 days]
-
A.
typeOfUnit
Indicates that one entity specifies the kind or category of measurement unit that the other entity belongs to.
-
B.
unitSystem
Indicates the system of measurement units (such as metric or imperial) that is used to quantify associated values or attributes.
-
C.
USUnit
Indicates that the associated quantity or measurement is expressed using United States customary units (e.g., feet, pounds, gallons) rather than other unit systems.
-
D.
unitOfMeasure
chosen
Indicates that one entity specifies the standard unit in which the quantity or value of another entity is measured.
-
E.
unitUK
Indicates that one entity uses or is measured in a unit of measure that is specific to or standard within the United Kingdom.
- 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_69c6884e15208190b9e91487eaafcf85 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6da3fa7fc8190a03e7132871a9af4 |
completed | March 27, 2026, 7:27 p.m. |
| PD | Predicate disambiguation | batch_69c6d7bb577c81908ee8b415b4281f3d |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:27 p.m.