Triple
T12108521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earthquake |
E288362
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Lorne Greene |
E229602
|
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: Lorne Greene | Statement: [Earthquake, starring, Lorne Greene]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lorne Greene Context triple: [Earthquake, starring, Lorne Greene]
-
A.
Lorne Greene
chosen
Lorne Greene was a Canadian actor best known for his role as patriarch Ben Cartwright on the classic television western series "Bonanza."
-
B.
Wayne Rogers
Wayne Rogers was an American actor best known for playing Captain "Trapper John" McIntyre on the television series M*A*S*H.
-
C.
William Conrad
William Conrad was an American actor and director best known for his deep, resonant voice and roles in radio, film, and television, including the TV series "Cannon" and "Jake and the Fatman."
-
D.
Garth Algar
Garth Algar is a shy, nerdy, and endearingly awkward best friend and co-host to Wayne Campbell in the comedy franchise "Wayne's World."
-
E.
Larry Lamb
Larry Lamb is an English actor and radio presenter best known for his roles in television series such as Gavin & Stacey and EastEnders.
- 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_69d6ab4a5c448190a110d1273314b21a |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915632dc48190863e0239cef37e24 |
completed | April 10, 2026, 3:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62a7fd708819090af422a60a69859 |
completed | May 2, 2026, 4:46 p.m. |
Created at: April 8, 2026, 9:49 p.m.