Triple
T19896320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metro (British newspaper) |
E478160
|
entity |
| Predicate | typicalFormatFeature |
P59120
|
FINISHED |
| Object | short headlines |
—
|
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: short headlines | Statement: [Metro (British newspaper), typicalFormatFeature, short headlines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalFormatFeature Context triple: [Metro (British newspaper), typicalFormatFeature, short headlines]
-
A.
featuresFormat
Indicates that something (such as a product, service, or medium) is presented, delivered, or made available in a particular format or configuration.
-
B.
typicalRecognitionFormat
Indicates the usual or standard format in which something is recognized, identified, or acknowledged.
-
C.
typicalUsageFormat
chosen
Indicates the usual or standard way in which something is expressed, presented, or formatted in practice.
-
D.
operatesInFormat
Indicates that an entity functions, performs its role, or is carried out using a specified format.
-
E.
typicalBroadcastFormat
Indicates the usual or standard broadcast format in which something (such as a program or content) is typically transmitted.
- 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_69d8e520682081909892916424699bd5 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6593dba78819082c8b80e65246171 |
completed | April 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69e537ecda248190895c96afb6243823 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:52 p.m.