Triple
T2017983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coat of arms of Yemen |
E44038
|
entity |
| Predicate | scrollPosition |
P34525
|
FINISHED |
| Object | clutched in the eagle’s talons |
—
|
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: clutched in the eagle’s talons | Statement: [Coat of arms of Yemen, scrollPosition, clutched in the eagle’s talons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scrollPosition Context triple: [Coat of arms of Yemen, scrollPosition, clutched in the eagle’s talons]
-
A.
positionHead
Indicates that one entity serves as the head or primary governing element in the positional or syntactic structure of another entity.
-
B.
currentHeight
Indicates the present vertical measurement or elevation of an entity at a given point in time.
-
C.
positionOn
Indicates that one entity is located on top of or at a specific place along the surface or extent of another entity.
-
D.
stylePositioning
Indicates how an entity is spatially or visually arranged or aligned relative to a reference frame or other elements.
-
E.
locationInDocument
Indicates that one entity specifies where another entity is situated or referenced within a document.
- F. None of above. chosen
Provenance (4 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_69a8891201bc8190aca837be6de41579 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb8ce71788190ac21beff10b08122 |
completed | March 7, 2026, 5:34 a.m. |
| PD | Predicate disambiguation | batch_69abb7a389408190a84a54856352f15b |
completed | March 7, 2026, 5:29 a.m. |
| PDg | Predicate description generation | batch_69abb83e7888819096dc40275c77daff |
completed | March 7, 2026, 5:31 a.m. |
Created at: March 4, 2026, 7:38 p.m.