Triple
T14350208
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fishscale |
E355832
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Shakey Dog |
E1094673
|
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: Shakey Dog | Statement: [Fishscale, hasPart, Shakey Dog]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shakey Dog Context triple: [Fishscale, hasPart, Shakey Dog]
-
A.
Shakey Dog
chosen
"Shakey Dog" is a storytelling-heavy hip-hop track by Ghostface Killah from his acclaimed album *Fishscale*, known for its vivid crime narrative and cinematic detail.
-
B.
Three Dog
Three Dog is the charismatic, freedom-fighting DJ of Galaxy News Radio in Fallout 3, known for his distinctive voice, moral commentary, and guidance to the Lone Wanderer.
-
C.
Bumpy Dog
Bumpy Dog is a loyal, excitable toy dog character from Enid Blyton’s Noddy stories, known for accompanying Noddy on his adventures in Toyland.
-
D.
Pooch
Pooch is a skilled and resourceful member of the elite black-ops team in the action film "The Losers."
-
E.
Mad Dog
Mad Dog is the vicious outlaw gunslinger and primary antagonist in the 1885 segment of the film "Back to the Future Part III."
- 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_69d82790a7e08190877e2d349b2e8d8e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8f4e1e588190bdc7aaf7a2819948 |
completed | April 14, 2026, 7:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd550aef908190a7ec49e409f92dc7 |
completed | May 8, 2026, 3:14 a.m. |
Created at: April 10, 2026, 1:14 a.m.