Triple
T14535344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louis Winthorpe III |
E341028
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object |
Duke & Duke
Duke & Duke is the wealthy, old-money Philadelphia commodities brokerage firm run by the Duke brothers in the film "Trading Places."
|
E1104813
|
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: Duke & Duke | Statement: [Louis Winthorpe III, employer, Duke & Duke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Duke & Duke Context triple: [Louis Winthorpe III, employer, Duke & Duke]
-
A.
Dukes
Dukes is a surname of English origin borne by various notable individuals across politics, sports, and the arts.
-
B.
Dukes
The Dukes are the athletic teams representing Duquesne University in collegiate sports competitions.
-
C.
Dukes
Dukes were high-ranking noble rulers within the Holy Roman Empire who held significant territorial authority and political influence, often participating in imperial institutions such as the Reichstag.
-
D.
The Dukes
The Dukes is an animated television series that follows the adventures of the Duke family from The Dukes of Hazzard in a more family-friendly, cartoon format.
-
E.
The Dukes
The Dukes are Steve Earle’s longtime backing band, known for their gritty blend of country, rock, and Americana on many of his recordings and tours.
- 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: Duke & Duke Triple: [Louis Winthorpe III, employer, Duke & Duke]
Generated description
Duke & Duke is the wealthy, old-money Philadelphia commodities brokerage firm run by the Duke brothers in the film "Trading Places."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Duke & Duke Target entity description: Duke & Duke is the wealthy, old-money Philadelphia commodities brokerage firm run by the Duke brothers in the film "Trading Places."
-
A.
Dukes
Dukes were high-ranking noble rulers within the Holy Roman Empire who held significant territorial authority and political influence, often participating in imperial institutions such as the Reichstag.
-
B.
Dukes
The Dukes are the athletic teams representing Duquesne University in collegiate sports competitions.
-
C.
Dukes
Dukes is a surname of English origin borne by various notable individuals across politics, sports, and the arts.
-
D.
The Dukes
The Dukes are Steve Earle’s longtime backing band, known for their gritty blend of country, rock, and Americana on many of his recordings and tours.
-
E.
The Dukes
The Dukes is a prominent theatre and arts venue in Lancaster, England, known for its diverse live performances and cultural 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_69d822dac79c8190a84a073f3cbaced5 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb1b9d39881908c7a3a5b17d432af |
completed | April 14, 2026, 9:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd7a589d488190b4a192f33d11092d |
completed | May 8, 2026, 5:53 a.m. |
| NEDg | Description generation | batch_69fd7ae2ce048190ba802c4639c128d6 |
completed | May 8, 2026, 5:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd7b7147448190952a395f72662014 |
completed | May 8, 2026, 5:58 a.m. |
Created at: April 10, 2026, 1:22 a.m.