Triple
T23947598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Classical Maya language |
E602955
|
entity |
| Predicate | scriptMedium |
P154461
|
FINISHED |
| Object | stone monuments |
—
|
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: stone monuments | Statement: [Classical Maya language, scriptMedium, stone monuments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptMedium Context triple: [Classical Maya language, scriptMedium, stone monuments]
-
A.
storyMedium
Indicates the medium or format through which a story is conveyed (e.g., book, film, audio).
-
B.
programMedium
Indicates the medium or channel through which a program is delivered or communicated (e.g., TV, radio, online).
-
C.
writesForMedium
Indicates that one entity creates written content intended for publication on a particular medium or platform.
-
D.
featuredMedium
Indicates that one medium (such as an image, video, or other media item) is highlighted or designated as the primary or representative media for another entity.
-
E.
script
Indicates that an entity is associated with a written text or code (such as a screenplay, program, or written instructions) that defines its content or behavior.
- F. None of above. chosen
Provenance (4 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_69e2953e4924819093f1c24c03476b42 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d02fb4fc8190835baf3bcf909d4d |
completed | April 29, 2026, 9:32 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
| PDg | Predicate description generation | batch_69f16e348b548190b76e50f9b611f76d |
completed | April 29, 2026, 2:34 a.m. |
Created at: April 17, 2026, 9:18 p.m.