Triple
T19764878
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Juan de Letrán |
E474726
|
entity |
| Predicate | hasNetworkCode |
P57366
|
FINISHED |
| Object | Line 8 station code (internal STC code) |
—
|
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: Line 8 station code (internal STC code) | Statement: [San Juan de Letrán, hasNetworkCode, Line 8 station code (internal STC code)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNetworkCode Context triple: [San Juan de Letrán, hasNetworkCode, Line 8 station code (internal STC code)]
-
A.
networkCode
chosen
Indicates that an entity is associated with, identified by, or operates under a specific network code within a communication or organizational network.
-
B.
hasNetworkName
Indicates that an entity is associated with a specific network identifier or name.
-
C.
hasIneCode
Indicates that an entity is associated with a specific INE (national statistics or education) code that identifies it in an official registry.
-
D.
hasCommunicationCodeType
Indicates that an entity is associated with a specific type or category of communication code (e.g., phone, fax, email, messaging).
-
E.
hasPrimaryNetwork
Indicates that an entity is associated with or connected to its main or most important network among potentially multiple networks.
- 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653226af081909992ff5568bb54a5 |
completed | April 20, 2026, 4:24 p.m. |
| PD | Predicate disambiguation | batch_69e5305016e08190b9561a96baecb0b8 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:48 p.m.