Triple
T34429128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castleknock railway station |
E883775
|
entity |
| Predicate | hasLanguageCodeForName |
P13919
|
FINISHED |
| Object | en |
—
|
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: en | Statement: [Castleknock railway station, hasLanguageCodeForName, en]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLanguageCodeForName Context triple: [Castleknock railway station, hasLanguageCodeForName, en]
-
A.
hasLanguageCodeFormat
Indicates that there is a specified structural or syntactic format that language codes associated with an entity must follow.
-
B.
hasCodenameLanguage
Indicates that a codename is expressed or defined in a particular language.
-
C.
hasLocaleName
Indicates that an entity has a specific name or label used in a particular language or regional locale.
-
D.
hasLinguisticCode
chosen
Indicates that an entity is associated with a specific linguistic identifier or code (such as a language or script code) that characterizes its linguistic properties.
-
E.
haveISO639Code
Indicates that a language or linguistic entity is associated with a specific ISO 639 standardized language code.
- 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_69f349c3dd2c819092cc9e64809f4a42 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff32b88bf48190b45afd1b60cb511c |
completed | May 9, 2026, 1:12 p.m. |
| PD | Predicate disambiguation | batch_69ff3031e18881908927b2ab452de863 |
completed | May 9, 2026, 1:01 p.m. |
Created at: May 1, 2026, 2 a.m.