Triple
T38588247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruins of Lordaeron |
E932392
|
entity |
| Predicate | languageDisplayed |
P145180
|
FINISHED |
| Object | Common (ruined human inscriptions) |
—
|
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: Common (ruined human inscriptions) | Statement: [Ruins of Lordaeron, languageDisplayed, Common (ruined human inscriptions)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageDisplayed Context triple: [Ruins of Lordaeron, languageDisplayed, Common (ruined human inscriptions)]
-
A.
languageDisplays
chosen
Indicates that one entity presents, shows, or renders another entity in a particular language or linguistic form.
-
B.
languageSystem
Indicates a relationship where an entity functions as or belongs to a particular system of language, such as a linguistic framework, code, or structured means of communication.
-
C.
languageVariant
Indicates that one language is a variant, dialect, or localized form of another language.
-
D.
navigationLanguage
Indicates the language used for navigation-related content, such as menus, directions, or interface controls.
-
E.
languageLabel
Indicates the human-readable name or label of a language associated with an entity or resource.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0224f4b6cc8190a8f79700a9af765f |
completed | May 11, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_6a0223f01eb081909419518fdd45f2a4 |
completed | May 11, 2026, 6:46 p.m. |
Created at: May 3, 2026, 4:32 p.m.