Triple
T34277475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Luther |
E879499
|
entity |
| Predicate | laterWorksForUnit |
P82664
|
FINISHED |
| Object | Serious and Serial Crime Unit |
—
|
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: Serious and Serial Crime Unit | Statement: [John Luther, laterWorksForUnit, Serious and Serial Crime Unit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterWorksForUnit Context triple: [John Luther, laterWorksForUnit, Serious and Serial Crime Unit]
-
A.
laterWorksAs
Indicates that an entity holds or takes on a particular occupation or role at a later point in time relative to another referenced time or role.
-
B.
laterWorkBy
Indicates that one work was created after another work by the same creator or author.
-
C.
laterWorksWith
Indicates that one entity collaborates or works together with another entity at a later time than some referenced or implied point.
-
D.
laterWorksAt
chosen
Indicates that an entity begins working at a place or organization at a time later than another referenced time or employment situation.
-
E.
laterWork
Indicates that one work was created, published, or produced after another work in time.
- F. None of above.
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_69f349b5f6648190b9420d94a4cd16e0 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a001adc8c108190ab3a43f6415e2be3 |
completed | May 10, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_6a001a290330819097c2c3123f9014b4 |
completed | May 10, 2026, 5:39 a.m. |
Created at: May 1, 2026, 1:56 a.m.