Triple
T19001417
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magic City |
E464961
|
entity |
| Predicate | notableFeatureHighlighted |
P61000
|
FINISHED |
| Object | skyline |
—
|
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: skyline | Statement: [Magic City, notableFeatureHighlighted, skyline]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableFeatureHighlighted Context triple: [Magic City, notableFeatureHighlighted, skyline]
-
A.
notableFeatureOn
chosen
Indicates that one entity is a prominent or distinguishing feature located on or part of another entity.
-
B.
notableFeatureInStory
Indicates that a particular feature, element, or characteristic plays a significant or prominent role within a story.
-
C.
notableTechnicalFeature
Indicates that an entity possesses a significant or distinguishing technical characteristic or capability.
-
D.
notableStyleFeature
Indicates that an entity possesses a distinctive stylistic characteristic or design element that is especially noteworthy or defining.
-
E.
notableFeat
Indicates that an entity is recognized for having achieved or performed a particularly significant or distinguished feat.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6863cf4819096e471d19f9a714c |
completed | April 20, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f88e0c81908cb20f08bf24cd32 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 12:01 p.m.