Triple
T17557441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HAL (Hypertext Application Language) |
E427622
|
entity |
| Predicate | linkHreflangKey |
P56371
|
FINISHED |
| Object | hreflang |
—
|
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: hreflang | Statement: [HAL (Hypertext Application Language), linkHreflangKey, hreflang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkHreflangKey Context triple: [HAL (Hypertext Application Language), linkHreflangKey, hreflang]
-
A.
linkedToLanguage
Indicates that an entity has an association or connection with a specific language, such as being expressed in, related to, or dependent on that language.
-
B.
linkType
Indicates the specific kind or category of relationship that connects two linked entities.
-
C.
languageCodeRelation
chosen
Indicates a relationship where one entity is associated with, identified by, or mapped to a specific language code of another entity.
-
D.
languageOfKeyText
Indicates that a specified language is the primary language in which a given key or central text is written.
-
E.
linksCountry
Indicates a relationship where one entity connects or associates another entity specifically with a country.
- 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_69d889df6dc081908f67dbadc03c07ee |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4562413d08190acaa5272046d3626 |
completed | April 19, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fb39948190a82a597c5bac5c57 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:50 a.m.