Triple
T18827093
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Robert Pierce |
E460415
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object |
Mary Pierce
Mary Pierce is a retired French-American professional tennis player and multiple Grand Slam singles and doubles champion.
|
E1344572
|
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: Mary Pierce | Statement: [Frank Robert Pierce, relative, Mary Pierce]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Pierce Context triple: [Frank Robert Pierce, relative, Mary Pierce]
-
A.
Sarah Pierce
Sarah Pierce was an early American educator best known for establishing one of the first and most influential schools for young women in the United States.
-
B.
Sarah Winston
Sarah Winston was a colonial American woman best known as the mother of Founding Father and second U.S. President John Adams.
-
C.
Serena Rathbun
Serena Rathbun is an American costume designer known for her work on films such as "Little Children" and "In the Bedroom."
-
D.
Althea
"Althea" is a beloved Grateful Dead song, known for its reflective lyrics, melodic guitar work, and enduring popularity in the band's live performances.
-
E.
Claire Devers
Claire Devers is a French film director and screenwriter known for her intimate, character-driven dramas and exploration of complex human relationships.
- 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: Mary Pierce Triple: [Frank Robert Pierce, relative, Mary Pierce]
Generated description
Mary Pierce is a retired French-American professional tennis player and multiple Grand Slam singles and doubles champion.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mary Pierce Target entity description: Mary Pierce is a retired French-American professional tennis player and multiple Grand Slam singles and doubles champion.
-
A.
Sarah Pierce
Sarah Pierce was an early American educator best known for establishing one of the first and most influential schools for young women in the United States.
-
B.
Sarah Winston
Sarah Winston was a colonial American woman best known as the mother of Founding Father and second U.S. President John Adams.
-
C.
Serena Rathbun
Serena Rathbun is an American costume designer known for her work on films such as "Little Children" and "In the Bedroom."
-
D.
Althea
"Althea" is a beloved Grateful Dead song, known for its reflective lyrics, melodic guitar work, and enduring popularity in the band's live performances.
-
E.
Claire Devers
Claire Devers is a French film director and screenwriter known for her intimate, character-driven dramas and exploration of complex human relationships.
- 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a6bfa4a88190b17d3118121414be |
completed | April 20, 2026, 4:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a055bd216d881908bee50901656372e |
completed | May 14, 2026, 5:21 a.m. |
| NEDg | Description generation | batch_6a0561e6500c8190b42d8257180ad7a6 |
completed | May 14, 2026, 5:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05623b880c81908fedf88e6a79ac31 |
completed | May 14, 2026, 5:48 a.m. |
Created at: April 10, 2026, 11:56 a.m.