Triple
T7854405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shenandoah |
E182135
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Katharine Ross |
E258567
|
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: Katharine Ross | Statement: [Shenandoah, starring, Katharine Ross]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Katharine Ross Context triple: [Shenandoah, starring, Katharine Ross]
-
A.
Katharine Ross
chosen
Katharine Ross is an American actress best known for her acclaimed role as Elaine Robinson in the classic 1967 film "The Graduate."
-
B.
Tanya Roberts
Tanya Roberts was an American actress and model best known for her roles in the James Bond film "A View to a Kill," the TV series "Charlie's Angels," and "That '70s Show."
-
C.
Suzy Parker
Suzy Parker was a prominent American fashion model and film actress of the 1950s and 1960s, celebrated as one of the first supermodels and a frequent face of major magazines and advertising campaigns.
-
D.
Gina Carter
Gina Carter is a British film and television producer known for her work on projects such as the period drama "Bright Young Things."
-
E.
Catherine Hicks
Catherine Hicks is an American actress best known for her role as Annie Camden on the long-running television series "7th Heaven."
- 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_69ca82869ee08190b8f9040dbc2c0467 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb1a72cfdc8190a3186c4c2894f571 |
completed | March 31, 2026, 12:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5b27e9b081909a0574458ddf43b0 |
completed | March 31, 2026, 5:27 a.m. |
Created at: March 30, 2026, 4:51 p.m.