Triple
T38370459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Girl loft |
E892561
|
entity |
| Predicate | inUniverseBuildingType |
P53535
|
FINISHED |
| Object | converted industrial loft |
—
|
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: converted industrial loft | Statement: [New Girl loft, inUniverseBuildingType, converted industrial loft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inUniverseBuildingType Context triple: [New Girl loft, inUniverseBuildingType, converted industrial loft]
-
A.
inUniverseType
Indicates that one entity exists within, or is categorized as belonging to, a particular fictional or conceptual universe type defined by the other entity.
-
B.
inUniverseLocationType
chosen
Indicates the type or category of location that something occupies within a fictional or defined universe or setting.
-
C.
containsBuildingType
Indicates that a location or area includes at least one building of the specified type.
-
D.
inUniverseMaker
Indicates that an entity exists or occurs within the fictional universe created or defined by another entity.
-
E.
inUniverseProductType
Indicates that a product belongs to or is categorized within a specific fictional or defined universe or setting.
- 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_69f76e47cb4c8190bdd92cd1db59c0c5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd884cb2b48190b6acd473430d9e19 |
completed | May 8, 2026, 6:53 a.m. |
| PD | Predicate disambiguation | batch_69fd8709ca208190a8bab836f0156af5 |
completed | May 8, 2026, 6:47 a.m. |
Created at: May 3, 2026, 4:31 p.m.