Triple
T6329076
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Weston |
E141930
|
entity |
| Predicate | hasFriend |
P8712
|
FINISHED |
| Object | Laverne Todd |
E139674
|
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: Laverne Todd | Statement: [Harry Weston, hasFriend, Laverne Todd]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laverne Todd Context triple: [Harry Weston, hasFriend, Laverne Todd]
-
A.
Laverne Todd
chosen
Laverne Todd is a central character on the American sitcom "Empty Nest," known as one of the key figures in the show's ensemble cast.
-
B.
Laverne Miller
Laverne Miller is a central character in the 1954 mystery film "Gorilla at Large," involved in the circus-themed plot surrounding a series of murders.
-
C.
Laverne
Laverne is a feminine given name most prominently associated in contemporary culture with actress and LGBTQ+ advocate Laverne Cox.
-
D.
Ronnie Fields
Ronnie Fields is a former American high school basketball phenom from Chicago known for his explosive athleticism and standout prep career in the 1990s.
-
E.
Darlene Hunt
Darlene Hunt is an American television writer and producer best known for creating the Showtime series "The Big C" and serving as an executive producer on various TV projects.
- 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_69c008d201748190917e69c41ba3f978 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0651197908190a30e504e2442d40f |
completed | March 22, 2026, 9:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c604154a1c8190b09e74cea2a18624 |
completed | March 27, 2026, 4:14 a.m. |
Created at: March 22, 2026, 4:30 p.m.