Triple
T14164685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harlan Dexter |
E351041
|
entity |
| Predicate | currentOccupationInStory |
P69186
|
FINISHED |
| Object | powerful businessman |
—
|
LITERAL 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: powerful businessman | Statement: [Harlan Dexter, currentOccupationInStory, powerful businessman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currentOccupationInStory Context triple: [Harlan Dexter, currentOccupationInStory, powerful businessman]
-
A.
hasOccupationDuringStory
chosen
Indicates that an entity holds or performs a particular occupation or job role during the time span covered by the story.
-
B.
currentPrimaryRole
Indicates the role an entity is presently holding as its main or most important function or position.
-
C.
roleInStories
Indicates the specific function, position, or character part an entity plays within one or more stories.
-
D.
narratorOccupation
Indicates that the specified occupation is the job or professional role held by the narrator.
-
E.
latestOccupation
Indicates the most recent job, role, or position that an entity currently holds or last held.
- 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_69d8278775fc8190b0802d22ca2f495d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61b207cc8190b85b1ff0910b54da |
completed | April 14, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69de05b8434c81908c33b1b513463b12 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 10, 2026, 12:59 a.m.