Triple
T4155553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ECB Main Building, Frankfurt |
E91405
|
entity |
| Predicate | numberOfEmployeesCapacity |
P17907
|
FINISHED |
| Object | about 2,900 |
—
|
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: about 2,900 | Statement: [ECB Main Building, Frankfurt, numberOfEmployeesCapacity, about 2,900]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfEmployeesCapacity Context triple: [ECB Main Building, Frankfurt, numberOfEmployeesCapacity, about 2,900]
-
A.
employsApproximateNumberOfPeople
chosen
Indicates that an entity employs a roughly estimated or approximate number of people, rather than an exact headcount.
-
B.
hasEmployees
Indicates that one entity employs one or more other entities as its workers or staff.
-
C.
seatingCapacity
Indicates the maximum number of people that something (typically a venue or vehicle) is designed or allowed to seat.
-
D.
staffSize
Indicates the number of staff members associated with an entity.
-
E.
typicalCapacity
Indicates the usual or standard amount, volume, or capability that something is designed or expected to hold, handle, or perform under normal conditions.
- 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_69aed9626ebc8190a39de631788bea3e |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0321eee88190871c1d4bf44a5007 |
completed | March 9, 2026, 5:28 p.m. |
| PD | Predicate disambiguation | batch_69af018dc90c8190a754b1bfbc802e80 |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:44 p.m.