Triple
T3544950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sela Ward |
E74972
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Anabella Sherman
Anabella Sherman is the daughter of American actress Sela Ward.
|
E368289
|
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: Anabella Sherman | Statement: [Sela Ward, hasChild, Anabella Sherman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anabella Sherman Context triple: [Sela Ward, hasChild, Anabella Sherman]
-
A.
Adeline Fisher
Adeline Fisher was the first wife of English composer Ralph Vaughan Williams and a supportive figure in his early personal and artistic life.
-
B.
Bella Thornton
Bella Thornton is the daughter of American actor, filmmaker, and musician Billy Bob Thornton.
-
C.
Alexis Morris
Alexis Morris is an American college basketball guard best known for starring at LSU and playing a pivotal role in the team’s 2023 national championship run.
-
D.
Madeline Ashton
Madeline Ashton is a vain, aging Hollywood actress whose obsession with youth and beauty leads her to drink a magical potion granting eternal life in the dark comedy film "Death Becomes Her."
-
E.
Aubrey Fitch
Aubrey Fitch was a U.S. Navy admiral and naval aviator who played a key leadership role in early World War II Pacific carrier operations.
- 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: Anabella Sherman Triple: [Sela Ward, hasChild, Anabella Sherman]
Generated description
Anabella Sherman is the daughter of American actress Sela Ward.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Anabella Sherman Target entity description: Anabella Sherman is the daughter of American actress Sela Ward.
-
A.
Adeline Fisher
Adeline Fisher was the first wife of English composer Ralph Vaughan Williams and a supportive figure in his early personal and artistic life.
-
B.
Bella Thornton
Bella Thornton is the daughter of American actor, filmmaker, and musician Billy Bob Thornton.
-
C.
Alexis Morris
Alexis Morris is an American college basketball guard best known for starring at LSU and playing a pivotal role in the team’s 2023 national championship run.
-
D.
Madeline Ashton
Madeline Ashton is a vain, aging Hollywood actress whose obsession with youth and beauty leads her to drink a magical potion granting eternal life in the dark comedy film "Death Becomes Her."
-
E.
Aubrey Fitch
Aubrey Fitch was a U.S. Navy admiral and naval aviator who played a key leadership role in early World War II Pacific carrier operations.
- 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_69ad85d274cc8190ab59c97298a1cfbf |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbf76c5b08190b898d31b80a3a350 |
completed | March 8, 2026, 6:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b38bdfe5748190b2de831635221ce1 |
completed | March 13, 2026, 4 a.m. |
| NEDg | Description generation | batch_69b38fda21fc81909b9ded36239abf93 |
completed | March 13, 2026, 4:17 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b39049e9cc81909ad74d33afe1985e |
completed | March 13, 2026, 4:19 a.m. |
Created at: March 8, 2026, 3:20 p.m.