Triple
T7222780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Year’s Eve Live on CNN |
E150299
|
entity |
| Predicate | hasFormerHost |
P46400
|
FINISHED |
| Object |
Erica Hill
Erica Hill is an American journalist and television news anchor known for her work on major networks including CNN and NBC.
|
E672940
|
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: Erica Hill | Statement: [New Year’s Eve Live on CNN, hasFormerHost, Erica Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erica Hill Context triple: [New Year’s Eve Live on CNN, hasFormerHost, Erica Hill]
-
A.
Erica Sayers
Erica Sayers is a character in the psychological thriller film "Black Swan," serving as the overbearing and emotionally manipulative mother of the protagonist, Nina.
-
B.
Erica Sutton
Erica Sutton is a supporting character in the romantic comedy film "40 Days and 40 Nights," involved in the protagonist's life during his vow of celibacy.
-
C.
Erica Huggins
Erica Huggins is a film producer known for her work on major Hollywood comedies and studio features.
-
D.
Erica Campbell
Erica Campbell is an American gospel singer, songwriter, and reality television personality best known as one half of the duo Mary Mary.
-
E.
Erica Bain
Erica Bain is the traumatized New York radio host who becomes a vigilante seeking justice after a brutal attack in the film "The Brave One."
- 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: Erica Hill Triple: [New Year’s Eve Live on CNN, hasFormerHost, Erica Hill]
Generated description
Erica Hill is an American journalist and television news anchor known for her work on major networks including CNN and NBC.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Erica Hill Target entity description: Erica Hill is an American journalist and television news anchor known for her work on major networks including CNN and NBC.
-
A.
Erica Sayers
Erica Sayers is a character in the psychological thriller film "Black Swan," serving as the overbearing and emotionally manipulative mother of the protagonist, Nina.
-
B.
Erica Sutton
Erica Sutton is a supporting character in the romantic comedy film "40 Days and 40 Nights," involved in the protagonist's life during his vow of celibacy.
-
C.
Erica Huggins
Erica Huggins is a film producer known for her work on major Hollywood comedies and studio features.
-
D.
Erica Campbell
Erica Campbell is an American gospel singer, songwriter, and reality television personality best known as one half of the duo Mary Mary.
-
E.
Erica Bain
Erica Bain is the traumatized New York radio host who becomes a vigilante seeking justice after a brutal attack in the film "The Brave One."
- 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_69c687effb44819092b95d07d0368c9f |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6e9b54a5c8190a4a289f32853a8fe |
completed | March 27, 2026, 8:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8569fbf4081909897b0e5456cd66a |
completed | March 28, 2026, 10:30 p.m. |
| NEDg | Description generation | batch_69c857ca74808190968fe68a0e4cc77b |
completed | March 28, 2026, 10:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c858184a0c81909ce2789371e37c05 |
completed | March 28, 2026, 10:37 p.m. |
Created at: March 27, 2026, 2:54 p.m.