Triple
T7458257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BT Tower |
E176179
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object |
Eric Bedford
Eric Bedford was a British architect best known for designing London’s iconic BT Tower in the 1960s.
|
E668397
|
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: Eric Bedford | Statement: [BT Tower, architect, Eric Bedford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eric Bedford Context triple: [BT Tower, architect, Eric Bedford]
-
A.
Fred Williamson
Fred Williamson is an American actor and former professional football player best known for his roles in 1970s blaxploitation films and numerous action and genre movies.
-
B.
Glen Tullman
Glen Tullman is an American healthcare technology entrepreneur and executive best known for leading and building major digital health companies, including Allscripts.
-
C.
Glenn Farr
Glenn Farr was an American film editor best known for his Academy Award–winning work on the 1983 film "Terms of Endearment."
-
D.
Roland Young
Roland Young was a British-born character actor best known for his urbane, often bemused comic roles in Hollywood films of the 1930s and 1940s, including the "Topper" series.
-
E.
Larry Russell
Larry Russell was an American composer best known for his Academy Award-winning work in film music.
- 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: Eric Bedford Triple: [BT Tower, architect, Eric Bedford]
Generated description
Eric Bedford was a British architect best known for designing London’s iconic BT Tower in the 1960s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Eric Bedford Target entity description: Eric Bedford was a British architect best known for designing London’s iconic BT Tower in the 1960s.
-
A.
Fred Williamson
Fred Williamson is an American actor and former professional football player best known for his roles in 1970s blaxploitation films and numerous action and genre movies.
-
B.
Glen Tullman
Glen Tullman is an American healthcare technology entrepreneur and executive best known for leading and building major digital health companies, including Allscripts.
-
C.
Glenn Farr
Glenn Farr was an American film editor best known for his Academy Award–winning work on the 1983 film "Terms of Endearment."
-
D.
Roland Young
Roland Young was a British-born character actor best known for his urbane, often bemused comic roles in Hollywood films of the 1930s and 1940s, including the "Topper" series.
-
E.
Larry Russell
Larry Russell was an American composer best known for his Academy Award-winning work in film music.
- 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_69c69f21632481908bf83f6c6da897e3 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f3b1f18881908140a6191d5478b5 |
completed | March 27, 2026, 9:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c83c5bab90819093431470e0e8c0e3 |
completed | March 28, 2026, 8:38 p.m. |
| NEDg | Description generation | batch_69c83e6bad30819094aeca19d5bcaa0c |
completed | March 28, 2026, 8:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c83f1e257c8190b027a15a132bc2d1 |
completed | March 28, 2026, 8:50 p.m. |
Created at: March 27, 2026, 3:35 p.m.