Triple
T29503814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basic |
E748454
|
entity |
| Predicate | headerFieldName |
P14546
|
FINISHED |
| Object | Authorization |
—
|
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: Authorization | Statement: [Basic, headerFieldName, Authorization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: headerFieldName Context triple: [Basic, headerFieldName, Authorization]
-
A.
headerField
Indicates that one entity is a specific header field (such as a name–value pair) belonging to or defined within another entity, typically a message, request, or document header.
-
B.
holderField
Indicates that a specified field or attribute belongs to, is maintained by, or is associated with a particular holder entity.
-
C.
fieldName
chosen
Indicates the specific name or label assigned to a field within a data structure, form, or record.
-
D.
headerValues
Indicates that one entity specifies or provides the set of values associated with a particular header in a structured message or data record.
-
E.
header
Indicates that one entity serves as a heading or title section that precedes and organizes the content of another entity.
- 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_69f0bd455a9c8190b40a3e8ea38cf61f |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66c34a370819089a89f26857d3dfa |
completed | May 2, 2026, 9:27 p.m. |
| PD | Predicate disambiguation | batch_69f6659b62fc8190b21555d0ba54db2d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 4:26 p.m.