Triple
T29423432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cairo |
E746215
|
entity |
| Predicate | supportsText |
P46417
|
FINISHED |
| Object | toy text API |
—
|
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: toy text API | Statement: [Cairo, supportsText, toy text API]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsText Context triple: [Cairo, supportsText, toy text API]
-
A.
supportsTextFormat
Indicates that one entity is capable of handling, rendering, or otherwise working with a specified text format.
-
B.
allowsText
chosen
Indicates that one entity permits or supports the use, input, or display of textual content in relation to another entity.
-
C.
supportsDocument
Indicates that one entity provides compatibility or functionality for handling, processing, or using a particular document or document type.
-
D.
supportsNarrativeText
Indicates that one entity provides justification, evidence, or contextual backing that helps explain or validate the narrative content expressed by another entity.
-
E.
usesTextService
Indicates that an entity makes use of a text-based service to perform some function or obtain some benefit.
- 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_69f0a7a06e0081908add494075912eb4 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e0f3d88190a4ee7b0673f1ef90 |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 28, 2026, 3:07 p.m.