Triple
T1398357
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SkyTeam |
E30721
|
entity |
| Predicate | allianceCategory |
P9451
|
FINISHED |
| Object | full-service airline alliance |
—
|
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: full-service airline alliance | Statement: [SkyTeam, allianceCategory, full-service airline alliance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allianceCategory Context triple: [SkyTeam, allianceCategory, full-service airline alliance]
-
A.
allianceType
chosen
Indicates the specific kind or category of alliance relationship that exists between entities.
-
B.
alliance
Indicates a formal cooperative relationship between entities who agree to support each other in shared goals or interests.
-
C.
allianceUse
Indicates that one party makes use of, benefits from, or leverages an alliance or allied relationship with another party.
-
D.
allianceStatus
Indicates the formal or informal cooperative relationship between entities, such as whether they are allies, neutral, or adversarial.
-
E.
allianceMember
Indicates that an entity is a member or participant in a specific alliance or coalition.
- 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_69a498fd4e408190bd73eca30ea9754c |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c382b6588190833c39ac84fb6139 |
completed | March 1, 2026, 10:53 p.m. |
| PD | Predicate disambiguation | batch_69a4bf017f8081908572121560ec621f |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.