Triple
T12530561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luke |
E299551
|
entity |
| Predicate | searchesFor |
P2773
|
FINISHED |
| Object | Lisa |
unclear NED1
|
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: Lisa | Statement: [Luke, searchesFor, Lisa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lisa Context triple: [Luke, searchesFor, Lisa]
-
A.
Lisa
Lisa is the central protagonist of the film "Wicker Park," around whom the story’s romantic mystery and emotional tension revolve.
-
B.
Lisa
Lisa is a fictional character from the psychological horror film "The Voices," known for her involvement with the disturbed protagonist and the film’s darkly comedic, violent events.
-
C.
Lisa
Lisa is a custom-designed integrated circuit that served as a key support chipset component in early Apple Macintosh computers, handling functions such as memory and system control.
-
D.
Lisa
Lisa is a person known primarily for holding a position or role that was later taken over by Denise.
-
E.
Lisa
"Lisa" is a notable work by control theorist and Stanford professor Stephen Boyd, likely associated with his research in optimization and control systems.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d6ada5cdd48190860d9ce30aff69be |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d95469d100819087c83bc55e3ec9ce |
completed | April 10, 2026, 7:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68ea78dcc819091773d900ad44be6 |
completed | May 2, 2026, 11:54 p.m. |
Created at: April 8, 2026, 9:57 p.m.