Triple
T11571437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | balancing rocks |
E274394
|
entity |
| Predicate | areVisuallySimilarTo |
P35666
|
FINISHED |
| Object | man-made rock balancing art |
—
|
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: man-made rock balancing art | Statement: [balancing rocks, areVisuallySimilarTo, man-made rock balancing art]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: areVisuallySimilarTo Context triple: [balancing rocks, areVisuallySimilarTo, man-made rock balancing art]
-
A.
lessSimilarTo
Indicates that one entity is considered to share fewer similarities or a weaker resemblance with another entity compared to some reference or alternative.
-
B.
hasSimilarityTo
Indicates that one entity shares common characteristics, features, or qualities with another entity to a notable degree.
-
C.
materiallySimilarTo
Indicates that two entities share substantially the same physical or material characteristics, composition, or properties, though they may not be exactly identical.
-
D.
similarToFlagOf
Indicates that one entity’s flag resembles or closely matches the design, colors, or symbols of another entity’s flag.
-
E.
resembles
chosen
Indicates that one entity is similar in appearance, form, or characteristics to another.
- 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_69d6aae5ac3c81908d2b0a3a665665b2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d88dd6913881908becf188c0a7a275 |
completed | April 10, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69d85dcbacd0819094d4a1237055affa |
completed | April 10, 2026, 2:17 a.m. |
Created at: April 8, 2026, 9:38 p.m.