Triple
T36978297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pilot Metropolitan |
E914754
|
entity |
| Predicate | inkCompatibility |
P179508
|
FINISHED |
| Object | water-based fountain pen ink |
—
|
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: water-based fountain pen ink | Statement: [Pilot Metropolitan, inkCompatibility, water-based fountain pen ink]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inkCompatibility Context triple: [Pilot Metropolitan, inkCompatibility, water-based fountain pen ink]
-
A.
crossCompatibility
chosen
Indicates that two entities are able to function, interact, or be used together successfully across different systems, versions, or contexts.
-
B.
datumCompatibility
Indicates that two data items or formats are suitable for use together without conflict, loss, or misinterpretation.
-
C.
enablesCompatibilityWith
Indicates that one entity provides the necessary features or conditions for another entity to function correctly or be compatible with a specified system, standard, or component.
-
D.
projectionCompatibility
Indicates that two or more projections (such as views, mappings, or representations) are mutually consistent and can be combined or used together without conflict.
-
E.
compatibleStand
Indicates that one entity can be properly supported or held by another entity’s stand or mounting system.
- 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_69f76e8d13b4819089af24a47ce092fc |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb34e5576881909394355c8ec6ddd2 |
completed | May 6, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69fb2f6171e88190bf1e0ee6a644b6a9 |
completed | May 6, 2026, 12:09 p.m. |
Created at: May 3, 2026, 4:14 p.m.