Triple
T8178189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Globalia |
E190992
|
entity |
| Predicate | hasSubsidiary |
P254
|
FINISHED |
| Object | Travelplan |
E716440
|
NE 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: Travelplan | Statement: [Globalia, hasSubsidiary, Travelplan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Travelplan Context triple: [Globalia, hasSubsidiary, Travelplan]
-
A.
Travelplan
chosen
Travelplan is a Spanish tour operator and travel services company that forms part of the Globalia tourism and aviation group.
-
B.
TripSavvy
TripSavvy is a travel-focused online publication offering destination guides, tips, and advice for travelers.
-
C.
Wikivoyage
Wikivoyage is a free, collaboratively edited online travel guide that provides up-to-date information and tips for destinations around the world.
-
D.
Trip
Trip is a 2017 psychedelic R&B concept album by Jhené Aiko that explores themes of grief, healing, and spiritual journey.
-
E.
GlobalFlyer
GlobalFlyer is a record-setting, single-pilot jet-powered aircraft designed by Burt Rutan and built by Scaled Composites to circumnavigate the globe nonstop without refueling.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca82c4538081909404325aa5639483 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4abb66bc81908d758c7af2e23ac6 |
completed | March 31, 2026, 4:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cced64c9588190b8db6452c364347d |
completed | April 1, 2026, 10:03 a.m. |
Created at: March 30, 2026, 5:40 p.m.