Triple
T144603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Willis Tower |
E2926
|
entity |
| Predicate | structuralSystem |
P4621
|
FINISHED |
| Object | bundled tube structure |
—
|
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: bundled tube structure | Statement: [Willis Tower, structuralSystem, bundled tube structure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: structuralSystem Context triple: [Willis Tower, structuralSystem, bundled tube structure]
-
A.
architectureType
Indicates the specific style or category of architecture that characterizes or defines an entity.
-
B.
buildingSection
Indicates a relationship where one entity is a specific section, part, or subdivision of a larger building.
-
C.
architecturalProject
Indicates that one entity is an architectural project associated with, created by, or undertaken for another entity.
-
D.
constructionMethod
Indicates the technique or process by which something is built, assembled, or created.
-
E.
architecture
chosen
Indicates the structural design or organizational framework that defines how components of a system or entity are arranged and interact.
- 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_69a2521e35c08190b28e5c9f1e3c9b59 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a257e935bc8190a03e54a10e9ba6f7 |
completed | Feb. 28, 2026, 2:50 a.m. |
| PD | Predicate disambiguation | batch_69a25656a4fc81908a87678ac3d28f93 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.