Triple
T22163686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zulema Zahir |
E547733
|
entity |
| Predicate | criminalActivityInFiction |
P96742
|
FINISHED |
| Object | robbery |
—
|
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: robbery | Statement: [Zulema Zahir, criminalActivityInFiction, robbery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: criminalActivityInFiction Context triple: [Zulema Zahir, criminalActivityInFiction, robbery]
-
A.
conductsInFiction
Indicates that an entity carries out or performs an action or role within a fictional context or narrative.
-
B.
criminalType
chosen
Indicates the specific category or classification of crime associated with a criminal act or offender.
-
C.
fictionalDetective
Indicates that the subject is a detective character who exists only in fiction rather than in real life.
-
D.
crimeListedInArticleIII
Indicates that a particular crime is one of the offenses expressly mentioned in Article III of the relevant constitution or legal document.
-
E.
createsInFiction
Indicates that one entity is the creator or originator of another entity within a fictional or narrative context.
- 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_69e11e3c4c5c81908d336165816b12e0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12a2f2f90819080b5bb73a6052c24 |
completed | April 28, 2026, 9:44 p.m. |
| PD | Predicate disambiguation | batch_69e71b41555881909b8e22718974d527 |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:34 p.m.