Triple
T12106960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doctor Dolittle |
E288326
|
entity |
| Predicate | hasPet |
P8711
|
FINISHED |
| Object |
Gub-Gub
Gub-Gub is a fictional talking pig and one of Doctor Dolittle’s most loyal animal companions in Hugh Lofting’s children’s book series.
|
E966819
|
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: Gub-Gub | Statement: [Doctor Dolittle, hasPet, Gub-Gub]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gub-Gub Context triple: [Doctor Dolittle, hasPet, Gub-Gub]
-
A.
Gooigi
Gooigi is a green, goo-like doppelgänger of Luigi from the Luigi’s Mansion series, used as a playable helper character to solve puzzles and reach otherwise inaccessible areas.
-
B.
Gugo
Gugo is the nickname of a person named Guglielmo, likely used informally by friends or family.
-
C.
Mungguy
Mungguy are the Aboriginal traditional owners and custodians of the land that includes Kakadu National Park in Australia’s Northern Territory.
-
D.
Gongnie
Gongnie was the personal name of King You of Zhou, the last king of the Western Zhou dynasty in ancient China.
-
E.
Mukmuk
Mukmuk is a small, marmot-inspired sidekick character who served as an unofficial mascot and fan favorite of the 2010 Winter Olympics in Vancouver.
- 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: Gub-Gub Triple: [Doctor Dolittle, hasPet, Gub-Gub]
Generated description
Gub-Gub is a fictional talking pig and one of Doctor Dolittle’s most loyal animal companions in Hugh Lofting’s children’s book series.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gub-Gub Target entity description: Gub-Gub is a fictional talking pig and one of Doctor Dolittle’s most loyal animal companions in Hugh Lofting’s children’s book series.
-
A.
Gooigi
Gooigi is a green, goo-like doppelgänger of Luigi from the Luigi’s Mansion series, used as a playable helper character to solve puzzles and reach otherwise inaccessible areas.
-
B.
Gugo
Gugo is the nickname of a person named Guglielmo, likely used informally by friends or family.
-
C.
Mungguy
Mungguy are the Aboriginal traditional owners and custodians of the land that includes Kakadu National Park in Australia’s Northern Territory.
-
D.
Gongnie
Gongnie was the personal name of King You of Zhou, the last king of the Western Zhou dynasty in ancient China.
-
E.
Mukmuk
Mukmuk is a small, marmot-inspired sidekick character who served as an unofficial mascot and fan favorite of the 2010 Winter Olympics in Vancouver.
- 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_69d6ab4a5c448190a110d1273314b21a |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d91561eaec819096ba00682d81f41a |
completed | April 10, 2026, 3:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f6795bf88190891acf918a432bef |
completed | May 2, 2026, 1:04 p.m. |
| NEDg | Description generation | batch_69f60263bc6c8190b867b4af20305e57 |
completed | May 2, 2026, 1:55 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6033935c08190980bd69395c250e4 |
completed | May 2, 2026, 1:59 p.m. |
Created at: April 8, 2026, 9:49 p.m.