Triple
T7893638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Recruit Holdings |
E183295
|
entity |
| Predicate | hasBrand |
P1500
|
FINISHED |
| Object | SUUMO |
E697380
|
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: SUUMO | Statement: [Recruit Holdings, hasBrand, SUUMO]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SUUMO Context triple: [Recruit Holdings, hasBrand, SUUMO]
-
A.
SUUMO
chosen
SUUMO is a major Japanese real estate information and housing search service brand operated by Recruit Holdings.
-
B.
DMM
DMM is the IATA airport code for King Fahd International Airport, the major international airport serving the Dammam region in Saudi Arabia.
-
C.
DMM
DMM is the United States Postal Service’s Domestic Mail Manual, which sets the official standards and regulations for mailing within the United States.
-
D.
Flytoget
Flytoget is Norway’s high-speed airport express train service that connects Oslo Airport with Oslo and surrounding areas.
-
E.
Cazoo
Cazoo is a UK-based online car retailer known for its high-profile sports sponsorships and rapid growth in the digital automotive marketplace.
- 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_69ca828c474c8190a254d6499871eaff |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a008fb88190a039fec40483ab93 |
completed | March 31, 2026, 3:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbdfc1b05481908af081f54bb1914d |
completed | March 31, 2026, 2:52 p.m. |
Created at: March 30, 2026, 5:01 p.m.