Triple
T463455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Capitol Records Building |
E7391
|
entity |
| Predicate | hasLightingPattern |
P1280
|
FINISHED |
| Object | spire lights used for special occasions |
—
|
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: spire lights used for special occasions | Statement: [Capitol Records Building, hasLightingPattern, spire lights used for special occasions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLightingPattern Context triple: [Capitol Records Building, hasLightingPattern, spire lights used for special occasions]
-
A.
hasLighting
chosen
Indicates that one entity is equipped with, contains, or is characterized by a particular type or configuration of lighting.
-
B.
hasTorchRelay
Indicates that an event or entity includes or is associated with a torch relay as part of its activities or proceedings.
-
C.
camouflagePattern
Indicates that one entity has a surface or visual design intended to conceal it by blending with its surroundings or disrupting its outline.
-
D.
hasBacklitKeyboard
Indicates that an entity is equipped with a keyboard that includes built-in lighting behind the keys.
-
E.
kitPattern
Indicates the design or visual pattern featured on a team's kit or uniform.
- 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_69a2e7e5c5bc8190a1dc8178218fba40 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2efc214788190a8dff20fec4412e0 |
completed | Feb. 28, 2026, 1:38 p.m. |
| PD | Predicate disambiguation | batch_69a2ede8eac081908dffade6a5e7950b |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.