Triple
T29928196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Concurs de Castells de Tarragona |
E760140
|
entity |
| Predicate | typicalStructures |
P86921
|
FINISHED |
| Object | 9-level human towers |
—
|
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: 9-level human towers | Statement: [Concurs de Castells de Tarragona, typicalStructures, 9-level human towers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalStructures Context triple: [Concurs de Castells de Tarragona, typicalStructures, 9-level human towers]
-
A.
typicalStructuralElement
chosen
Indicates that one entity is a standard or characteristic structural component commonly found within or forming part of another entity.
-
B.
commonStructure
Indicates that two or more entities share the same or a very similar internal organization, pattern, or arrangement.
-
C.
traditionalStructureIncludes
Indicates that a traditional structure contains, incorporates, or is composed of the specified component or element.
-
D.
standStructure
Indicates that one entity is a vertical support or upright structural element for another entity.
-
E.
definesStructure
Indicates that one entity specifies or determines the organizational form, composition, or arrangement of another entity.
- 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_69f224631674819080c8d089674f9f4f |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a03173dd4988190a38175b63cba9f09 |
completed | May 12, 2026, 12:04 p.m. |
| PD | Predicate disambiguation | batch_6a031700ade88190afd217d5966b03b4 |
completed | May 12, 2026, 12:03 p.m. |
Created at: April 29, 2026, 6:17 p.m.