Triple
T15284115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Huxley |
E365348
|
entity |
| Predicate | loveInterest |
P7325
|
FINISHED |
| Object | Susan Vance |
E366890
|
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: Susan Vance | Statement: [David Huxley, loveInterest, Susan Vance]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Susan Vance Context triple: [David Huxley, loveInterest, Susan Vance]
-
A.
Susan Vance
chosen
Susan Vance is the free-spirited, chaotic heiress played by Katharine Hepburn in the classic screwball comedy film "Bringing Up Baby."
-
B.
Susan Miller
Susan Miller is a film producer best known for her work on the fantasy romantic comedy "Ella Enchanted."
-
C.
Susan Ivey
Susan Ivey is a fictional character from the 2001 dark comedy film "Novocaine."
-
D.
Betsy McCaughey
Betsy McCaughey is an American politician, writer, and former Lieutenant Governor of New York known for her conservative commentary and opposition to certain health care reforms.
-
E.
Susan Ward
Susan Ward is an American actress and former model best known for her roles in late-1990s and early-2000s films and television series.
- 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_69d85a103d9081908c1ea6c4c73ac8e3 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00e53c9588190a6cb61ac8805c706 |
completed | April 15, 2026, 10:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feef798a588190981c77e6f4c6be78 |
completed | May 9, 2026, 8:25 a.m. |
Created at: April 10, 2026, 3:15 a.m.