Triple
T1189532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flatiron Building |
E25324
|
entity |
| Predicate | façadeFeature |
P19771
|
FINISHED |
| Object | ornate terra-cotta detailing |
—
|
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: ornate terra-cotta detailing | Statement: [Flatiron Building, façadeFeature, ornate terra-cotta detailing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: façadeFeature Context triple: [Flatiron Building, façadeFeature, ornate terra-cotta detailing]
-
A.
façadeOrientation
Indicates the directional orientation that a building’s façade faces relative to a reference (e.g., cardinal directions or a main street).
-
B.
exteriorFeature
chosen
Indicates a relationship where one entity serves as an external or outward-facing feature, element, or characteristic of another entity.
-
C.
roofFeature
Indicates that one entity is a feature, element, or characteristic that is part of or associated with a roof.
-
D.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
E.
façadeInscriptionTextWelsh
Indicates that the text inscribed on a façade is written in Welsh.
- 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_69a49427d98881908646d6c63b8cea1e |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd57c3c481908bdca483fcaa3297 |
completed | March 1, 2026, 10:27 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5bacc481909e8dfd5215e4711a |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.