Triple
T33924494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pazyryk carpet |
E869709
|
entity |
| Predicate | knotDensity |
P147497
|
FINISHED |
| Object | high knot density |
—
|
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: high knot density | Statement: [Pazyryk carpet, knotDensity, high knot density]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: knotDensity Context triple: [Pazyryk carpet, knotDensity, high knot density]
-
A.
carpetKnotDensity
chosen
Indicates the number of knots per unit area in a carpet, reflecting how densely the carpet is knotted.
-
B.
usesCordWithKnots
Indicates that one entity employs a cord that has been tied with knots in relation to another entity or action.
-
C.
hasKnotType
Indicates that one entity is characterized by, or associated with, a specific type or classification of knot.
-
D.
numberOfStitches
Indicates the count of individual stitches involved in or required by an item, process, or event.
-
E.
furDensity
Indicates the thickness or concentration of fur covering an entity’s body or a specific body part.
- 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_69f349992c508190aa4afa24a086cc8c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:49 a.m.