Triple
T16100110
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgia Ford |
E390592
|
entity |
| Predicate | notableRelative |
P367
|
FINISHED |
| Object | Melissa Mathison |
—
|
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 Mathison | Statement: [Georgia Ford, notableRelative, Melissa Mathison]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Melissa Mathison Context triple: [Georgia Ford, notableRelative, Melissa Mathison]
-
A.
Melissa Mathison
chosen
Melissa Mathison was an American screenwriter best known for writing the screenplay for Steven Spielberg’s film "E.T. the Extra-Terrestrial."
-
B.
Melissa McKnight
Melissa McKnight is a British-American former model and actress best known as the ex-wife of "Friends" star Matt LeBlanc.
-
C.
Melissa Loya
Melissa Loya is known as the wife of Episcopal bishop Craig Loya.
-
D.
Melissa Blake
Melissa Blake is a television writer and producer known for her work on series such as "Heroes" and "Ghost Whisperer."
-
E.
Melissa Franklin
Melissa Franklin is a Canadian-American experimental particle physicist known for her work at CERN and as the first woman to receive tenure in Harvard University's physics department.
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1ff6756948190a7f5ecb375e59701 |
completed | April 17, 2026, 9:37 a.m. |
Created at: April 10, 2026, 5 a.m.