Triple
T132992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States flag |
E2690
|
entity |
| Predicate | displayOrientation |
P1101
|
FINISHED |
| Object | stars in upper left when hung horizontally |
—
|
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: stars in upper left when hung horizontally | Statement: [United States flag, displayOrientation, stars in upper left when hung horizontally]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: displayOrientation Context triple: [United States flag, displayOrientation, stars in upper left when hung horizontally]
-
A.
orientation
chosen
Indicates the relative directional alignment or facing of one entity with respect to another or to a reference frame.
-
B.
displayedWith
Indicates that one entity is shown or presented together alongside another entity in the same context or view.
-
C.
aspectRatio
Indicates the proportional relationship between an entity’s width and its height.
-
D.
hasNumberOfScreens
Indicates the quantity of screens associated with or contained in a given entity.
-
E.
displayedAt
Indicates that one entity is presented or exhibited at a particular location, venue, or event.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a25855baf48190a1b63f2e5865d957 |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a2564edb488190974dc00eb9ac37d9 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.