Triple
T16714153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jesse Helms |
E406179
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object |
WRAL radio
WRAL radio is a Raleigh, North Carolina–based radio station historically known for its conservative commentary and as an early platform for future U.S. Senator Jesse Helms.
|
E1228853
|
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: WRAL radio | Statement: [Jesse Helms, employer, WRAL radio]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WRAL radio Context triple: [Jesse Helms, employer, WRAL radio]
-
A.
WJLA-TV
WJLA-TV is a Washington, D.C.–based television station that serves as the local ABC network affiliate.
-
B.
WTN
WTN is the IATA airport code for RAF Waddington, a Royal Air Force station in Lincolnshire, England.
-
C.
WBAL (AM)
WBAL (AM) is a long-running Baltimore-based news/talk radio station known for its local news, sports coverage, and public affairs programming.
-
D.
WRBW
WRBW is a television station in Orlando, Florida, serving the local market with syndicated and network programming.
-
E.
WLIB
WLIB is a New York City AM radio station known for its urban contemporary gospel and talk programming, serving primarily African American and Caribbean audiences.
- 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: WRAL radio Triple: [Jesse Helms, employer, WRAL radio]
Generated description
WRAL radio is a Raleigh, North Carolina–based radio station historically known for its conservative commentary and as an early platform for future U.S. Senator Jesse Helms.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: WRAL radio Target entity description: WRAL radio is a Raleigh, North Carolina–based radio station historically known for its conservative commentary and as an early platform for future U.S. Senator Jesse Helms.
-
A.
WJLA-TV
WJLA-TV is a Washington, D.C.–based television station that serves as the local ABC network affiliate.
-
B.
WTN
WTN is the IATA airport code for RAF Waddington, a Royal Air Force station in Lincolnshire, England.
-
C.
WBAL (AM)
WBAL (AM) is a long-running Baltimore-based news/talk radio station known for its local news, sports coverage, and public affairs programming.
-
D.
WRBW
WRBW is a television station in Orlando, Florida, serving the local market with syndicated and network programming.
-
E.
WLIB
WLIB is a New York City AM radio station known for its urban contemporary gospel and talk programming, serving primarily African American and Caribbean audiences.
- 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_69d8838f242881908abd8bc138795886 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e38653cdd48190863e1cc989e21f39 |
completed | April 18, 2026, 1:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0091ab9e54819097e71ce1616b28b5 |
completed | May 10, 2026, 2:09 p.m. |
| NEDg | Description generation | batch_6a00923f1da08190b6b2c869284099bc |
completed | May 10, 2026, 2:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00931aa1d88190a0775e74779b3a6b |
completed | May 10, 2026, 2:15 p.m. |
Created at: April 10, 2026, 5:20 a.m.