Triple
T164916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broadway Limited |
E2991
|
entity |
| Predicate | travelClass |
P3037
|
FINISHED |
| Object | first class |
—
|
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: first class | Statement: [Broadway Limited, travelClass, first class]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: travelClass Context triple: [Broadway Limited, travelClass, first class]
-
A.
travelPreference
Indicates a person's favored way or style of traveling, such as preferred modes, conditions, or arrangements for trips.
-
B.
tourismType
Indicates the specific category or kind of tourism activity or experience associated with an entity.
-
C.
tourismRegion
Indicates that a place or area is designated or recognized as a tourism region associated with another geographic or administrative entity.
-
D.
hasCabinClass
chosen
Indicates that an entity (such as a booking, ticket, or seat) is associated with a specific cabin class (e.g., economy, business, first).
-
E.
explores
Indicates actively investigating, traveling through, or examining something in order to discover or learn more about it.
- 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_69a2524ce1e48190ab066bf72859f474 |
completed | Feb. 28, 2026, 2:26 a.m. |
| NER | Named-entity recognition | batch_69a258827da481909b20ea5e9d21676f |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a25664ba8081908ac298511a9fc5ba |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:34 a.m.