Triple
T27818006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Victor Comstock |
E702732
|
entity |
| Predicate | basedInCityInFiction |
P86009
|
FINISHED |
| Object | Pittsburgh |
—
|
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: Pittsburgh | Statement: [Victor Comstock, basedInCityInFiction, Pittsburgh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedInCityInFiction Context triple: [Victor Comstock, basedInCityInFiction, Pittsburgh]
-
A.
basedInFictionalWorkLocation
Indicates that an entity’s location or setting is situated within a fictional place as depicted in a specific creative work.
-
B.
basedInFictionalLocation
Indicates that an entity’s primary setting, origin, or operations occur in a fictional (non-real) location.
-
C.
cityOfFictionalOrigin
chosen
Indicates the city from which a fictional character, entity, or work is described as originating within its narrative or fictional universe.
-
D.
townOfFictionalSetting
Indicates that a town serves as the fictional setting or primary location where the events of a narrative work take place.
-
E.
cityOfFictionalLocation
Indicates that a fictional location is situated within or associated with a particular city.
- 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_69ef840ad1e88190b5bff2d1ddec8700 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: April 27, 2026, 5:46 p.m.