Triple
T33857872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Room 309 |
E867835
|
entity |
| Predicate | partOfBuildingFloor |
P66281
|
FINISHED |
| Object | third floor of Havemeyer Hall |
—
|
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: third floor of Havemeyer Hall | Statement: [Room 309, partOfBuildingFloor, third floor of Havemeyer Hall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfBuildingFloor Context triple: [Room 309, partOfBuildingFloor, third floor of Havemeyer Hall]
-
A.
locatedInBuildingFloorCount
Indicates that one entity is located in or associated with a building characterized by a specific number of floors.
-
B.
partOfFacility
chosen
Indicates that one entity is a component, section, or sub-unit belonging to a larger facility.
-
C.
floorAbove
Indicates that one floor is located directly above another floor in a vertical arrangement.
-
D.
occupiesFloorsOf
Indicates that one entity uses or takes up multiple levels or stories within a building or structure.
-
E.
hasFloor
Indicates that one entity possesses, includes, or is associated with a particular floor or level within a structure.
- 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_69f349943ccc8190a3c41a3e0ae46cbf |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a0019b0e9fc81909494320f05e81742 |
completed | May 10, 2026, 5:37 a.m. |
| PD | Predicate disambiguation | batch_6a00193379e0819096d1985686ce10e3 |
completed | May 10, 2026, 5:35 a.m. |
Created at: May 1, 2026, 1:47 a.m.