Triple
T20610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cloud Gate |
E408
|
entity |
| Predicate | maintenance |
P1580
|
FINISHED |
| Object | requires regular cleaning |
—
|
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: requires regular cleaning | Statement: [Cloud Gate, maintenance, requires regular cleaning]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintenance Context triple: [Cloud Gate, maintenance, requires regular cleaning]
-
A.
status
Indicates the current condition, state, or standing of an entity within a given context.
-
B.
system
Indicates that an entity functions as or belongs to a structured, organized set of components or processes that operate together as a system.
-
C.
mission
Indicates that an entity is assigned or engaged in a specific task, operation, or purpose-directed undertaking.
-
D.
requires
Indicates that one entity must exist, occur, or be satisfied before another entity can exist, occur, or be carried out.
-
E.
restriction
Indicates a limiting condition or rule that constrains or controls what an entity can do, use, or access in relation to another entity or context.
- F. None of above. chosen
Provenance (4 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_69a240778d288190815c0052ebbbcc91 |
completed | Feb. 28, 2026, 1:10 a.m. |
| NER | Named-entity recognition | batch_69a246f7bd30819085f751c41f6f029e |
completed | Feb. 28, 2026, 1:37 a.m. |
| PD | Predicate disambiguation | batch_69a246526f5881909bc2a46e978bd082 |
completed | Feb. 28, 2026, 1:35 a.m. |
| PDg | Predicate description generation | batch_69a246f4d7908190a947f6da251c6f3b |
completed | Feb. 28, 2026, 1:37 a.m. |
Created at: Feb. 28, 2026, 1:14 a.m.