Triple
T38418542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magic Carpet aliyah |
E903164
|
entity |
| Predicate | airlineUsed |
P190858
|
FINISHED |
| Object | Alaska Airlines |
—
|
NE NERFINISHED |
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: Alaska Airlines | Statement: [Magic Carpet aliyah, airlineUsed, Alaska Airlines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airlineUsed Context triple: [Magic Carpet aliyah, airlineUsed, Alaska Airlines]
-
A.
airline
Indicates that an entity operates as a commercial air transport carrier providing flight services between locations.
-
B.
userAirlineIATAName
Indicates that a user is associated with an airline identified by its IATA code and corresponding airline name.
-
C.
airlineContext
Indicates a relationship, situation, or action that specifically occurs within or is constrained by an airline-related context (such as flights, carriers, or air travel operations).
-
D.
airlinesUse
Indicates that certain airlines operate, employ, or make use of a specified resource, service, or system.
-
E.
usedByAirlineIATA
Indicates that something (such as a code, resource, or facility) is utilized or operated by an airline identified by its IATA code.
- 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_69f76e67e4fc8190a7d08dfe9a8af998 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
| PDg | Predicate description generation | batch_69fcd148e6d4819082c118832ecc599b |
completed | May 7, 2026, 5:52 p.m. |
Created at: May 3, 2026, 4:31 p.m.