Triple
T18637948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jane March |
E455603
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Stalker |
—
|
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: Stalker | Statement: [Jane March, notableWork, Stalker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stalker Context triple: [Jane March, notableWork, Stalker]
-
A.
Stalker
Stalker is a 1979 Soviet science fiction art film by Andrei Tarkovsky that follows a guide leading two men through a mysterious forbidden zone said to grant one’s deepest desires.
-
B.
Stalker
chosen
Stalker is an American psychological thriller television series centered on a specialized LAPD unit that investigates stalking-related crimes.
-
C.
Stalker (TV series)
Stalker is an American psychological thriller television series that follows a specialized LAPD unit investigating stalking cases, starring Dylan McDermott and Maggie Q.
-
D.
Wasteland
Wasteland is a post-apocalyptic comic series written by Antony Johnston, noted for its bleak world-building and long-form storytelling.
-
E.
Wasteland
Wasteland is a harsh, desolate region in the Jak and Daxter video game series, known for its dangerous terrain, hostile inhabitants, and role as a major battleground.
- 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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54fc9fa6c81909e1b988bdfb5ebcc |
completed | April 19, 2026, 9:57 p.m. |
Created at: April 10, 2026, 11:47 a.m.