Triple
T2473614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joan W. and Irving B. Harris |
E55033
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object |
Joan W. Harris
Joan W. Harris was a Chicago-based philanthropist and arts patron known for her leadership and major contributions to cultural and educational institutions.
|
E270835
|
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: Joan W. Harris | Statement: [Joan W. and Irving B. Harris, hasMember, Joan W. Harris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joan W. Harris Context triple: [Joan W. and Irving B. Harris, hasMember, Joan W. Harris]
-
A.
Rosemary Harris
Rosemary Harris is a British actress acclaimed for her extensive stage and screen career, including a Tony Award win and an Academy Award nomination.
-
B.
Christianna Brand
Christianna Brand was a British crime and children's author best known for her "Nurse Matilda" stories, which inspired the film "Nanny McPhee."
-
C.
Astrid Lindley
Astrid Lindley is known as the wife of late Pro Football Hall of Famer and broadcaster Frank Gifford.
-
D.
Doreen Brett
Doreen Brett was the wife of British comedian and actor Norman Wisdom.
-
E.
Lucinda Riley
Lucinda Riley was a bestselling Irish author best known for her multi-volume historical fiction series "The Seven Sisters," which achieved international acclaim.
- 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: Joan W. Harris Triple: [Joan W. and Irving B. Harris, hasMember, Joan W. Harris]
Generated description
Joan W. Harris was a Chicago-based philanthropist and arts patron known for her leadership and major contributions to cultural and educational institutions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Joan W. Harris Target entity description: Joan W. Harris was a Chicago-based philanthropist and arts patron known for her leadership and major contributions to cultural and educational institutions.
-
A.
Rosemary Harris
Rosemary Harris is a British actress acclaimed for her extensive stage and screen career, including a Tony Award win and an Academy Award nomination.
-
B.
Christianna Brand
Christianna Brand was a British crime and children's author best known for her "Nurse Matilda" stories, which inspired the film "Nanny McPhee."
-
C.
Astrid Lindley
Astrid Lindley is known as the wife of late Pro Football Hall of Famer and broadcaster Frank Gifford.
-
D.
Doreen Brett
Doreen Brett was the wife of British comedian and actor Norman Wisdom.
-
E.
Lucinda Riley
Lucinda Riley was a bestselling Irish author best known for her multi-volume historical fiction series "The Seven Sisters," which achieved international acclaim.
- 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_69ab49e279e88190ab10d7248aea9d11 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd149c10c819098ff75f176972c8b |
completed | March 7, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af17a8d87c819084637958a5dc4028 |
completed | March 9, 2026, 6:55 p.m. |
| NEDg | Description generation | batch_69af1b3bb8908190a48c6190f9f9a488 |
completed | March 9, 2026, 7:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69af1c404d248190b4444eaed46e63da |
completed | March 9, 2026, 7:15 p.m. |
Created at: March 6, 2026, 9:45 p.m.