Triple
T20417135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Lee Hancock |
E500741
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Melissa Hancock |
—
|
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: Melissa Hancock | Statement: [John Lee Hancock, spouse, Melissa Hancock]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Melissa Hancock Context triple: [John Lee Hancock, spouse, Melissa Hancock]
-
A.
Melissa Hancock
chosen
Melissa Hancock is known as the wife of American filmmaker John Lee Hancock, recognized for his work as a director and screenwriter.
-
B.
Linda McDonough
Linda McDonough is a film producer best known for her work on the science fiction movie adaptation of "Ender's Game."
-
C.
Betsy Hassett
Betsy Hassett is a New Zealand international footballer and midfielder who has represented her country at multiple FIFA Women’s World Cups and Olympic Games.
-
D.
Myra Hurd
Myra Hurd is a British psychologist and academic known for her contributions to cognitive and developmental psychology.
-
E.
Elinor Quarles
Elinor Quarles is a central fictional character in Aldous Huxley’s novel "Point Counter Point," representing the emotional and moral complexities of modern relationships.
- 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_69e0b4a935588190b9446a99b37ced44 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67a4437448190b07b6e6e3de5830f |
completed | April 20, 2026, 7:11 p.m. |
Created at: April 16, 2026, 11:30 a.m.