Triple
T17142393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Domino Recording Company |
E415999
|
entity |
| Predicate | notableArtist |
P601
|
FINISHED |
| Object | Franz Ferdinand |
E391174
|
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: Franz Ferdinand | Statement: [Domino Recording Company, notableArtist, Franz Ferdinand]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Franz Ferdinand Context triple: [Domino Recording Company, notableArtist, Franz Ferdinand]
-
A.
Franz Ferdinand
chosen
Franz Ferdinand is a Scottish indie rock band known for their danceable post-punk revival sound and breakthrough hit "Take Me Out."
-
B.
Roye
Roye is a commune in northern France, located in the Somme department within the Hauts-de-France region.
-
C.
Roye
Roye is a given name and surname, typically considered a variant spelling of the name Roy.
-
D.
Donovan
Donovan is a common Irish surname that has been borne by notable figures in politics, sports, and the arts.
-
E.
Donovan
Donovan is a human character in Isaac Asimov’s science fiction short story “Catch That Rabbit,” serving as one of the technicians who work with and oversee the behavior of experimental robots.
- 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f2d5de10819090cbd65661b018d3 |
completed | April 18, 2026, 9:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a014154b9848190ac01602eb01ae710 |
completed | May 11, 2026, 2:39 a.m. |
Created at: April 10, 2026, 5:36 a.m.