Triple
T3356268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Standard of Saint Lucia |
E70611
|
entity |
| Predicate | displayRestriction |
P14632
|
FINISHED |
| Object | not flown when the monarch is not in Saint Lucia |
—
|
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: not flown when the monarch is not in Saint Lucia | Statement: [Royal Standard of Saint Lucia, displayRestriction, not flown when the monarch is not in Saint Lucia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: displayRestriction Context triple: [Royal Standard of Saint Lucia, displayRestriction, not flown when the monarch is not in Saint Lucia]
-
A.
displayMode
Indicates how content or information is visually presented or arranged to the user.
-
B.
displayRule
chosen
Indicates the rule or condition that determines how something should be visually presented or displayed.
-
C.
displayState
Indicates the current visual or presentation status of an item, such as whether and how it is shown, hidden, or rendered in a user interface or display context.
-
D.
displayType
Indicates the manner or format in which something is presented, shown, or rendered.
-
E.
displays
Indicates that one entity visually presents or shows another entity’s content or information.
- 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_69ad85a660c48190998489309a3b4869 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb242d4988190bbac993df587936d |
completed | March 8, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69ada42fbe7c8190b9f185b5ab985f17 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.