Triple
T25119991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | yácata |
E629238
|
entity |
| Predicate | terraces |
P23536
|
FINISHED |
| Object | multiple levels |
—
|
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: multiple levels | Statement: [yácata, terraces, multiple levels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terraces Context triple: [yácata, terraces, multiple levels]
-
A.
usedTerracing
Indicates that an entity employed terracing techniques, such as creating stepped or leveled surfaces, in carrying out an activity or modifying land.
-
B.
numberOfTerraces
chosen
Indicates the total count of terraces associated with a given entity.
-
C.
formsTerraceWith
Indicates that one entity combines or aligns with another to create or constitute a terrace-like structure or formation.
-
D.
terracesSymbolize
Indicates that terraces serve as symbols or representations of certain ideas, values, or meanings within a given context.
-
E.
hasTerracedWalls
Indicates that an entity possesses walls that are constructed in stepped or terraced levels rather than as a single continuous vertical surface.
- 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_69e2ff3288048190bd82c3b7f7bd0e62 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f465ca9a088190911a49d5117b67d8 |
completed | May 1, 2026, 8:35 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:27 a.m.