Triple
T34549729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Código Postal de México |
E887028
|
entity |
| Predicate | firstDigitIndicates |
P35107
|
FINISHED |
| Object | state or large geographic region |
—
|
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: state or large geographic region | Statement: [Código Postal de México, firstDigitIndicates, state or large geographic region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstDigitIndicates Context triple: [Código Postal de México, firstDigitIndicates, state or large geographic region]
-
A.
firstDigitEncoding
chosen
Indicates that one entity encodes or represents the first digit of another entity (such as a number, code, or identifier).
-
B.
secondDigitRepresents
Indicates that the second digit in a numeric or coded value encodes or signifies a specific attribute, category, or meaning within that value.
-
C.
hasTensDigitOne
Indicates that the tens digit of a given number is equal to one.
-
D.
digitType
Indicates the specific category or kind of digit (such as numerical, symbolic, or positional type) associated with an entity.
-
E.
isFirstNumberOneFor
Indicates that the first number in a given pair, sequence, or context is equal to one for the associated entity or situation.
- 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_69f349cff89081908f91e0b064f4833e |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379fd7aac8190873077e63873aa72 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 2:02 a.m.