Triple
T3847761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PKX |
E85213
|
entity |
| Predicate | terminalDesign |
P51909
|
FINISHED |
| Object | starfish-shaped terminal |
—
|
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: starfish-shaped terminal | Statement: [PKX, terminalDesign, starfish-shaped terminal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terminalDesign Context triple: [PKX, terminalDesign, starfish-shaped terminal]
-
A.
terminal
Indicates that one entity is the final or end point in a process, sequence, or structure, beyond which no further continuation occurs.
-
B.
terminal3Use
Indicates that an entity makes use of or operates from terminal 3 (such as a specific terminal in a facility, station, or airport).
-
C.
terminalArea
Indicates that one entity is a designated terminal area or zone associated with another entity (such as a facility, system, or region).
-
D.
frontDesign
Indicates that one entity serves as the primary or visible front-facing design or appearance of another entity.
-
E.
TerminalEUsedFor
Indicates that a terminal E is used for a particular purpose, function, or activity.
- 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_69aed936de1c81908f91bed80f70abb2 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeebcc8a0481909c35161336bdfbf9 |
completed | March 9, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69aee750377c8190af70c79768c0edd8 |
completed | March 9, 2026, 3:29 p.m. |
| PDg | Predicate description generation | batch_69aee8d9b328819080158be59e5bcc97 |
completed | March 9, 2026, 3:35 p.m. |
Created at: March 9, 2026, 3:18 p.m.