Triple
T22724214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Power |
E561947
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Lela Loren |
—
|
NE NERFINISHED |
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: Lela Loren | Statement: [Power, starring, Lela Loren]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lela Loren Context triple: [Power, starring, Lela Loren]
-
A.
Lela Loren
chosen
Lela Loren is an American actress best known for her role as Angela Valdes on the crime drama television series "Power."
-
B.
Diana Sands
Diana Sands was an acclaimed American stage and screen actress best known for her groundbreaking performance in the original Broadway production and film adaptation of "A Raisin in the Sun."
-
C.
Luana Patten
Luana Patten was an American child actress best known for her early work in Walt Disney films during the 1940s and 1950s.
-
D.
Jo Harlow
Jo Harlow is a technology executive best known for leading mobile device and smartphone businesses at companies such as Nokia and later Microsoft.
-
E.
Lala Ward
Lala Ward is a British actress best known for playing the Time Lady Romana in the long-running science fiction television series Doctor Who.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17928a21c8190a1b888754ba7808b |
completed | April 29, 2026, 3:21 a.m. |
Created at: April 17, 2026, 3:20 p.m.