Triple
T13333853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NFL Live |
E317638
|
entity |
| Predicate | hasHost |
P2592
|
FINISHED |
| Object |
Laura Rutledge
Laura Rutledge is an American sports journalist and television host for ESPN, best known for her work covering the NFL and college football.
|
E1051009
|
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: Laura Rutledge | Statement: [NFL Live, hasHost, Laura Rutledge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laura Rutledge Context triple: [NFL Live, hasHost, Laura Rutledge]
-
A.
Marta Heflin
Marta Heflin was an American actress best known for her roles in several of Robert Altman’s ensemble films during the 1970s and 1980s.
-
B.
Susan Brewer
Susan Brewer is an American artist and the former wife of actor Peter Fonda.
-
C.
Kelly Loeffler
Kelly Loeffler is an American businesswoman and Republican politician who briefly served as a U.S. Senator from Georgia after being appointed to the seat in 2019.
-
D.
Ken Loeffler
Ken Loeffler was an American basketball coach best known for leading La Salle University to national prominence in the 1950s and for his successful stints in both college and professional basketball.
-
E.
Abigail Gowdy
Abigail Gowdy is the daughter of former U.S. Congressman and federal prosecutor Trey Gowdy.
- 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: Laura Rutledge Triple: [NFL Live, hasHost, Laura Rutledge]
Generated description
Laura Rutledge is an American sports journalist and television host for ESPN, best known for her work covering the NFL and college football.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Laura Rutledge Target entity description: Laura Rutledge is an American sports journalist and television host for ESPN, best known for her work covering the NFL and college football.
-
A.
Marta Heflin
Marta Heflin was an American actress best known for her roles in several of Robert Altman’s ensemble films during the 1970s and 1980s.
-
B.
Susan Brewer
Susan Brewer is an American artist and the former wife of actor Peter Fonda.
-
C.
Kelly Loeffler
Kelly Loeffler is an American businesswoman and Republican politician who briefly served as a U.S. Senator from Georgia after being appointed to the seat in 2019.
-
D.
Ken Loeffler
Ken Loeffler was an American basketball coach best known for leading La Salle University to national prominence in the 1950s and for his successful stints in both college and professional basketball.
-
E.
Abigail Gowdy
Abigail Gowdy is the daughter of former U.S. Congressman and federal prosecutor Trey Gowdy.
- 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_69d806b4d62c81908d4ced1665414be5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99cff44e08190b9583baf0b626e42 |
completed | April 11, 2026, 12:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f77f7a13508190bbab6eb68fb52a18 |
completed | May 3, 2026, 5:01 p.m. |
| NEDg | Description generation | batch_69f78058d4c88190be75e0a38cdc20da |
completed | May 3, 2026, 5:05 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f78157b9cc8190a1855cb9715aa7d5 |
completed | May 3, 2026, 5:09 p.m. |
Created at: April 9, 2026, 9:30 p.m.