Triple
T10846635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abby Park |
E256027
|
entity |
| Predicate | closeFriendOf |
P8712
|
FINISHED |
| Object | Miriam Mendelsohn |
E316906
|
NE FINISHED |
How this triple was built (2 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: Miriam Mendelsohn | Statement: [Abby Park, closeFriendOf, Miriam Mendelsohn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Miriam Mendelsohn Context triple: [Abby Park, closeFriendOf, Miriam Mendelsohn]
-
A.
Miriam Mendelsohn
chosen
Miriam Mendelsohn is a loyal, upbeat, and supportive best friend of Mei Lee in Pixar's animated film "Turning Red."
-
B.
Miriam Fried
Miriam Fried is an acclaimed Israeli-American violinist renowned for her solo performances, chamber music collaborations, and influential teaching career.
-
C.
Miriam Bienstock
Miriam Bienstock was an American music industry executive and co-founder of Atlantic Records who played a key role in shaping the label’s early business operations and success.
-
D.
Miriam Weinstein
Miriam Weinstein is the mother of film producer Harvey Weinstein, whose first name inspired the name of the film company Miramax.
-
E.
Helene Shapiro
Helene Shapiro is an American mathematician known for her work in linear algebra and matrix theory, and as a student of Olga Taussky-Todd.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6aa81a5d08190aa86689061d1ddd2 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d750d132e081909c977b3dc4110ca4 |
completed | April 9, 2026, 7:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4417f4dfc8190bd50cec0bc52a9cc |
completed | April 19, 2026, 2:44 a.m. |
Created at: April 8, 2026, 9:20 p.m.