Triple
T16379521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Spanish Princess |
E397762
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Laura Carmichael |
E1059822
|
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: Laura Carmichael | Statement: [The Spanish Princess, stars, Laura Carmichael]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laura Carmichael Context triple: [The Spanish Princess, stars, Laura Carmichael]
-
A.
Laura Carmichael
chosen
Laura Carmichael is a British actress best known for her role as Lady Edith Crawley in the television series "Downton Abbey."
-
B.
Anne Durkan
Anne Durkan is a notable individual associated with the Durkan family name, recognized as a bearer of this surname.
-
C.
Tessa Menzies
Tessa Menzies is a child of California politician and governor Gavin Newsom.
-
D.
Rachel Daly
Rachel Daly is an English professional footballer known for her versatility as both a forward and defender, with a prominent club career in the NWSL and WSL and regular appearances for the England national team.
-
E.
Elisabeth Waterston
Elisabeth Waterston is an American actress known for her work in film, television, and theater, and as a member of the Waterston acting family.
- 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e319da3c6c8190a9ccf744996c31e8 |
completed | April 18, 2026, 5:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a015fb40dc08190b9d6a04f3c19f57d |
completed | May 11, 2026, 4:48 a.m. |
Created at: April 10, 2026, 5:08 a.m.