Triple
T14300971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bannerman Road gang |
E354560
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object |
K9
K9 is a robotic dog companion from the Doctor Who universe, known for his advanced intelligence, loyalty, and frequent assistance to the Bannerman Road gang and other protagonists.
|
E71121
|
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: K9 | Statement: [Bannerman Road gang, hasMember, K9]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: K9 Context triple: [Bannerman Road gang, hasMember, K9]
-
A.
K-9
K-9 is a 1989 American buddy cop comedy film starring James Belushi as a detective partnered with a police dog to take down a drug dealer.
-
B.
K-9
K-9 is a robotic dog from the Doctor Who universe, known as a loyal, intelligent companion equipped with advanced technology and weaponry.
-
C.
K9K
K9K is a Canadian postal code prefix assigned to part of the city of Peterborough in Ontario.
-
D.
K-99
K-99 is a north–south state highway running through eastern Kansas, connecting several small towns and rural areas.
-
E.
K9FIN Moukari
K9FIN Moukari is a Finnish-modified version of the South Korean K9 Thunder self-propelled howitzer, tailored to meet Finland’s specific operational and environmental requirements.
- 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: K9 Triple: [Bannerman Road gang, hasMember, K9]
Generated description
K9 is a robotic dog companion from the Doctor Who universe, known for his advanced intelligence, loyalty, and frequent assistance to the Bannerman Road gang and other protagonists.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: K9 Target entity description: K9 is a robotic dog companion from the Doctor Who universe, known for his advanced intelligence, loyalty, and frequent assistance to the Bannerman Road gang and other protagonists.
-
A.
K-9
K-9 is a 1989 American buddy cop comedy film starring James Belushi as a detective partnered with a police dog to take down a drug dealer.
-
B.
K-9
chosen
K-9 is a robotic dog from the Doctor Who universe, known as a loyal, intelligent companion equipped with advanced technology and weaponry.
-
C.
K9K
K9K is a Canadian postal code prefix assigned to part of the city of Peterborough in Ontario.
-
D.
K-99
K-99 is a north–south state highway running through eastern Kansas, connecting several small towns and rural areas.
-
E.
K9FIN Moukari
K9FIN Moukari is a Finnish-modified version of the South Korean K9 Thunder self-propelled howitzer, tailored to meet Finland’s specific operational and environmental requirements.
- F. None of above.
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_69d8278e17088190b328c5a9d4be74ff |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de717e246c819083e67ac2b3b77881 |
completed | April 14, 2026, 4:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd647daf448190a7a9e4ab432977c4 |
completed | May 8, 2026, 4:20 a.m. |
| NEDg | Description generation | batch_69fd6539793881909d1fd3985c171837 |
completed | May 8, 2026, 4:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd65c06fc88190a7d2a84d7858b20f |
completed | May 8, 2026, 4:25 a.m. |
Created at: April 10, 2026, 1:11 a.m.