Triple
T35210885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Lone Wolf in Mexico |
E1016671
|
entity |
| Predicate | hasProtagonistPastOccupation |
P35945
|
FINISHED |
| Object | jewel thief |
—
|
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: jewel thief | Statement: [The Lone Wolf in Mexico, hasProtagonistPastOccupation, jewel thief]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProtagonistPastOccupation Context triple: [The Lone Wolf in Mexico, hasProtagonistPastOccupation, jewel thief]
-
A.
characterFormerOccupation
chosen
Indicates that a character previously held a specific occupation but no longer does.
-
B.
hasOccupationDuringStory
Indicates that an entity holds or performs a particular occupation or job role during the time span covered by the story.
-
C.
otherProtagonistOccupation
Indicates that another main character in the narrative has a specific occupation or job role.
-
D.
protagonistParentOccupation
Indicates the occupation or job held by the protagonist’s parent in the described context.
-
E.
hasPastOccupation
Indicates that an entity previously held a particular job, role, or occupation in the past.
- 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_69f76ddf549c8190869d0af076fd2c28 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a036fb4650c81908df9b9ec8ed8594b |
completed | May 12, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_6a036f64dc648190a31cf944d3ea0f7d |
completed | May 12, 2026, 6:20 p.m. |
Created at: May 3, 2026, 4:02 p.m.