Triple
T5206407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sacsayhuamán |
E117520
|
entity |
| Predicate | stoneFitting |
P62014
|
FINISHED |
| Object | dry stone construction without mortar |
—
|
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: dry stone construction without mortar | Statement: [Sacsayhuamán, stoneFitting, dry stone construction without mortar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stoneFitting Context triple: [Sacsayhuamán, stoneFitting, dry stone construction without mortar]
-
A.
stoneTransportMethod
Indicates the means or method by which a stone is transported from one place to another.
-
B.
foundationStoneLaid
Indicates that the initial, symbolic stone marking the start of constructing a building or structure has been formally placed.
-
C.
stoneColor
Indicates that one entity has a particular color attribute associated with a stone.
-
D.
stoneFragmentsFrom
Indicates that one entity consists of or originates as stone fragments derived from another entity.
-
E.
rebuiltInStone
Indicates that a previously existing structure was reconstructed using stone as the primary building material.
- 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_69bd4463dd3c81909966123f20b79d57 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7a4a7b7c8190af5a7149f8fe4f87 |
completed | March 20, 2026, 4:48 p.m. |
| PD | Predicate disambiguation | batch_69bd77bb4e8c819094b5ac7cf61512f9 |
completed | March 20, 2026, 4:37 p.m. |
| PDg | Predicate description generation | batch_69bd79000cf88190b3c05d95395b0cd2 |
completed | March 20, 2026, 4:42 p.m. |
Created at: March 20, 2026, 1:47 p.m.