Triple
T10982317
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Memorial Stadium |
E259537
|
entity |
| Predicate | rockMConstructedFrom |
P1326
|
FINISHED |
| Object | rocks from the original football field bleachers |
—
|
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: rocks from the original football field bleachers | Statement: [Memorial Stadium, rockMConstructedFrom, rocks from the original football field bleachers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rockMConstructedFrom Context triple: [Memorial Stadium, rockMConstructedFrom, rocks from the original football field bleachers]
-
A.
hasRockType
chosen
Indicates that an entity is composed of, characterized by, or associated with a specific type of rock.
-
B.
rockTypeMarketedAs
Indicates that a particular rock type is promoted or advertised under a specific commercial or trade name.
-
C.
cliffMaterial
Indicates that a cliff is composed of or primarily made from a specified material.
-
D.
hasRockTalusAtBase
Indicates that a rock talus deposit is present at the base of something, typically accumulating at the bottom of a slope, cliff, or similar feature.
-
E.
rockHeight
Indicates that a rock has a specified vertical measurement or elevation (its height).
- 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d772eb518c8190a885a417815f2ff6 |
completed | April 9, 2026, 9:35 a.m. |
| PD | Predicate disambiguation | batch_69d72e9055908190b438f039574aaaaf |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:24 p.m.