Triple
T16570794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carol Hathaway |
E402576
|
entity |
| Predicate | worksWith |
P398
|
FINISHED |
| Object | Susan Lewis |
—
|
NE NERFINISHED |
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: Susan Lewis | Statement: [Carol Hathaway, worksWith, Susan Lewis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Susan Lewis Context triple: [Carol Hathaway, worksWith, Susan Lewis]
-
A.
Susan Lewis
chosen
Susan Lewis is a fictional emergency physician and central character on the television series "ER," known for her dedication, compassion, and complex personal storylines.
-
B.
Susie Lewis
Susie Lewis is an animator and producer best known for her work on the MTV animated series "Daria."
-
C.
Karen Lewis
Karen Lewis is a film and television producer known for her work on the project "Exile."
-
D.
Karen Lewis
Karen Lewis is a British television producer best known for her work on acclaimed drama series such as "Last Tango in Halifax."
-
E.
Karen Lewis
Karen Lewis is a television producer known for her work on the British drama series "Years and Years."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8838648088190acf97ef11fc3f61b |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35958d49c8190b995188240fb355b |
completed | April 18, 2026, 10:13 a.m. |
Created at: April 10, 2026, 5:16 a.m.