Triple
T25513097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States ZIP code system |
E639434
|
entity |
| Predicate | extendedFormatName |
P103637
|
FINISHED |
| Object | ZIP+4 |
—
|
NE NERFINISHED |
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: ZIP+4 | Statement: [United States ZIP code system, extendedFormatName, ZIP+4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: extendedFormatName Context triple: [United States ZIP code system, extendedFormatName, ZIP+4]
-
A.
expandedVersionForm
chosen
Indicates that one entity is an expanded or more fully written-out version of another entity’s form.
-
B.
codenameFormat
Indicates that an entity’s codename follows a specific prescribed format or pattern.
-
C.
expandedForm
Indicates that one representation is the expanded or fully written-out form of another, typically decomposing it into a sum or more detailed expression.
-
D.
registryFormat
Indicates that one entity specifies the data format or schema used for registering another entity in a registry.
-
E.
usedFormat
Indicates that one entity employs or applies a particular format or representation in relation to 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_69e75dbe32e48190a62d749a0ff2a96a |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f82fe30881909915c13a183be6c3 |
completed | May 2, 2026, 1:12 p.m. |
| PD | Predicate disambiguation | batch_69f49377411c8190b2188de444d76795 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 21, 2026, 2:53 p.m.