Triple
T22142248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anton Lesser |
E547189
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Harry Lesser |
—
|
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: Harry Lesser | Statement: [Anton Lesser, child, Harry Lesser]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Lesser Context triple: [Anton Lesser, child, Harry Lesser]
-
A.
Harry Lesser
chosen
Harry Lesser is the son of acclaimed English actor Anton Lesser.
-
B.
Harry Kleiner
Harry Kleiner was an American screenwriter known for his work on notable films such as the crime thriller "Bullitt."
-
C.
Harry Weltman
Harry Weltman is a former professional basketball executive best known for his leadership roles with American Basketball Association and NBA franchises.
-
D.
Philip Liebmann
Philip Liebmann was the husband of American film actress Linda Darnell.
-
E.
Harry Korshak
Harry Korshak is a film producer best known for his work on the biographical drama "Gable and Lombard."
- 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_69e11e3a95d88190a3bd80d9471976c3 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129bf78108190b50d937917258693 |
completed | April 28, 2026, 9:42 p.m. |
Created at: April 16, 2026, 8:32 p.m.