Triple
T12613439
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Helen McCrory |
E301185
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Gulliver Lewis |
E301185
|
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: Gulliver Lewis | Statement: [Helen McCrory, child, Gulliver Lewis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gulliver Lewis Context triple: [Helen McCrory, child, Gulliver Lewis]
-
A.
Gulliver Lewis
chosen
Gulliver Lewis is the son of the late British actress Helen McCrory and actor Damian Lewis.
-
B.
Gulliver McGrath
Gulliver McGrath is an Australian actor known for his roles as a child and young teen in films such as Dark Shadows and Hugo.
-
C.
Henry Limpet
Henry Limpet is a timid, nearsighted Brooklyn bookkeeper who magically transforms into a talking fish and becomes an unlikely World War II hero in the film "The Incredible Mr. Limpet."
-
D.
Harry Gribbon
Harry Gribbon was an American vaudeville and film comedian best known for his slapstick roles in silent and early sound comedies.
-
E.
Mac Wilkins
Mac Wilkins is an American discus thrower and Olympic gold medalist renowned for setting multiple world records in the 1970s.
- 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_69d7bdeaf49c8190b13800111fa77ea3 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d960c2e5b88190a7cc16002b218d8a |
completed | April 10, 2026, 8:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65ed1044c8190bbe881d32a4bf29e |
completed | May 2, 2026, 8:30 p.m. |
Created at: April 9, 2026, 5:12 p.m.