Triple
T17363717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Infant Island |
E422133
|
entity |
| Predicate | languageOfFictionalInhabitants |
P70771
|
FINISHED |
| Object | Infant Island native language |
—
|
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: Infant Island native language | Statement: [Infant Island, languageOfFictionalInhabitants, Infant Island native language]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfFictionalInhabitants Context triple: [Infant Island, languageOfFictionalInhabitants, Infant Island native language]
-
A.
languageOfFictionalUniverse
Indicates the language used or spoken within a fictional universe or setting.
-
B.
hasLanguageInUniverse
chosen
Indicates that a particular language exists or is used within a specified fictional or conceptual universe.
-
C.
hasFictionalInhabitants
Indicates that a place or setting is inhabited by fictional or imaginary beings.
-
D.
fictionalLanguage
Indicates a relationship where an entity uses, is expressed in, or is associated with a language that is invented or does not exist in reality.
-
E.
areSpokenIn
Indicates that a particular language is used as a spoken means of communication within a specified region, community, or context.
- 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_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a4f52988190847230e119a35b87 |
completed | April 19, 2026, 2:13 a.m. |
| PD | Predicate disambiguation | batch_69e3b02662d08190a07d0fb5c04b6f33 |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:44 a.m.