Triple
T2401245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mosaic 4 |
E47772
|
entity |
| Predicate | loyaltyDomain |
P37955
|
FINISHED |
| Object | air travel |
—
|
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: air travel | Statement: [Mosaic 4, loyaltyDomain, air travel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: loyaltyDomain Context triple: [Mosaic 4, loyaltyDomain, air travel]
-
A.
loyaltyProgramType
Indicates the specific category or kind of loyalty program associated with an entity (such as points-based, tiered, or subscription-based).
-
B.
loyaltyProgramEarnings
Indicates the amount or details of rewards or benefits a participant accrues within a loyalty or rewards program.
-
C.
loyaltyProgramTierOf
Indicates the specific loyalty or rewards program tier that an entity (such as a customer or account) belongs to.
-
D.
supportsLoyaltyCards
Indicates that an entity provides functionality to accept, manage, or work with loyalty cards for rewards or benefits.
-
E.
loyaltyConflict
Indicates a situation where an entity’s loyalties to different people, groups, or principles are in tension or opposition, creating a conflict in choosing whom or what to support.
- 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_69a88a1c450c81909f61abb8b6863885 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc8caf12c8190b1482b9bc7bf9606 |
completed | March 7, 2026, 6:42 a.m. |
| PD | Predicate disambiguation | batch_69abc5a3825c81909ec6111dfc165453 |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abc664317c8190a6bb5a5065c21bde |
completed | March 7, 2026, 6:32 a.m. |
Created at: March 4, 2026, 7:57 p.m.