Triple
T4404703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Hall (Library of Congress) |
E93699
|
entity |
| Predicate | floorCountServed |
P20990
|
FINISHED |
| Object | multiple levels of the Thomas Jefferson Building |
—
|
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: multiple levels of the Thomas Jefferson Building | Statement: [Great Hall (Library of Congress), floorCountServed, multiple levels of the Thomas Jefferson Building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floorCountServed Context triple: [Great Hall (Library of Congress), floorCountServed, multiple levels of the Thomas Jefferson Building]
-
A.
floorCount
Indicates the number of floors or levels that a building or structure has.
-
B.
numberOfFloorsServed
chosen
Indicates the total count of distinct floors that are served or accessed by a given entity (such as an elevator or service system).
-
C.
numberOfFloors
Indicates the total count of distinct floor levels that a building or structure has.
-
D.
floorCountOfSurroundingBuildings
Indicates the number of floors in the buildings that are located around or near a given reference building or area.
-
E.
floorCountIncludingBasement
Indicates the total number of floors in a building, counting all above-ground levels plus any basement levels.
- 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_69b345158c748190a2c040fce2da9980 |
completed | March 12, 2026, 10:58 p.m. |
| NER | Named-entity recognition | batch_69b35488d5b8819087370dd77249aefb |
completed | March 13, 2026, 12:04 a.m. |
| PD | Predicate disambiguation | batch_69b34f5b36a881909bf2e970aa523390 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:28 p.m.