Triple
T24937048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael James |
E623341
|
entity |
| Predicate | colleaguePortrayedBy |
P159396
|
FINISHED |
| Object | Peter Sellers |
—
|
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: Peter Sellers | Statement: [Michael James, colleaguePortrayedBy, Peter Sellers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: colleaguePortrayedBy Context triple: [Michael James, colleaguePortrayedBy, Peter Sellers]
-
A.
professorPortrayedBy
Indicates that a professor character is depicted or played by a specific person in a work (e.g., film, TV, or other media).
-
B.
alsoPortrayedBy
Indicates that the same role or character is portrayed by an additional, different performer or actor.
-
C.
partnerPortrayedBy
Indicates that one entity is the actor or performer who portrays the partner or counterpart of another entity in a work.
-
D.
portrayedBy
Indicates that one entity serves as the actor or performer who represents or plays the role of another entity in a work or medium.
-
E.
friendPortrayedBy
Indicates that a person’s friend is depicted or represented by a particular actor or performer.
- F. None of above. chosen
Provenance (4 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_69e2fac6b5a48190a1c38857f00915a9 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f584f07b648190aee894c1d5320bc3 |
completed | May 2, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_69f4a0edd10c81908a052ab864d57c54 |
completed | May 1, 2026, 12:47 p.m. |
| PDg | Predicate description generation | batch_69f55e497fa081909bc59a7b92c5df59 |
completed | May 2, 2026, 2:15 a.m. |
Created at: April 18, 2026, 5:30 a.m.