Triple
T20704431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | go! (Hawaii) |
E508862
|
entity |
| Predicate | operatedUnderBrand |
P1501
|
FINISHED |
| Object |
go! brand
go! brand was the marketing name used by Mesa Airlines for its short-lived inter-island low-cost carrier service in Hawaii.
|
E1445970
|
NE FINISHED |
How this triple was built (4 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: go! brand | Statement: [go! (Hawaii), operatedUnderBrand, go! brand]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: go! brand Context triple: [go! (Hawaii), operatedUnderBrand, go! brand]
-
A.
Go!
"Go!" is a high-energy song featured on the album "Be," known for its upbeat tempo and motivational tone.
-
B.
Go!
Go! is a classic 1962 hard bop jazz album by tenor saxophonist Dexter Gordon, widely regarded as one of his finest and most accessible recordings.
-
C.
The Brand
"The Brand" is one of the nonfiction essays in David Grann’s collection *The Devil and Sherlock Holmes*, likely focusing on a gripping real-world mystery or crime investigation.
-
D.
Goc
Goc is a German surname most notably associated with professional ice hockey players such as Marcel Goc.
-
E.
9Go!
9Go! is an Australian free-to-air digital television multichannel owned by the Nine Network, primarily targeting children, teenagers, and young adults with entertainment programming.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: go! brand Triple: [go! (Hawaii), operatedUnderBrand, go! brand]
Generated description
go! brand was the marketing name used by Mesa Airlines for its short-lived inter-island low-cost carrier service in Hawaii.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: go! brand Target entity description: go! brand was the marketing name used by Mesa Airlines for its short-lived inter-island low-cost carrier service in Hawaii.
-
A.
Go!
"Go!" is a high-energy song featured on the album "Be," known for its upbeat tempo and motivational tone.
-
B.
Go!
Go! is a classic 1962 hard bop jazz album by tenor saxophonist Dexter Gordon, widely regarded as one of his finest and most accessible recordings.
-
C.
The Brand
"The Brand" is one of the nonfiction essays in David Grann’s collection *The Devil and Sherlock Holmes*, likely focusing on a gripping real-world mystery or crime investigation.
-
D.
Goc
Goc is a German surname most notably associated with professional ice hockey players such as Marcel Goc.
-
E.
9Go!
9Go! is an Australian free-to-air digital television multichannel owned by the Nine Network, primarily targeting children, teenagers, and young adults with entertainment programming.
- F. None of above. chosen
Provenance (5 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_69e0b4c2b2a481909e31e9cb8f81ab55 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c18ea874819092a125d9f929a311 |
completed | April 21, 2026, 12:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08d7f268688190a21d24d474c6a0c2 |
completed | May 16, 2026, 8:47 p.m. |
| NEDg | Description generation | batch_6a08da96db5c8190a6ebcb02dac005ae |
completed | May 16, 2026, 8:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08db03b1008190893b27189731e134 |
completed | May 16, 2026, 9 p.m. |
Created at: April 16, 2026, 12:13 p.m.