Triple
T21520282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lockheed Martin X-27 |
E530956
|
entity |
| Predicate | isConceptualOnly |
P68355
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Lockheed Martin X-27, isConceptualOnly, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isConceptualOnly Context triple: [Lockheed Martin X-27, isConceptualOnly, true]
-
A.
isConceptual
chosen
Indicates that something exists as an abstract or theoretical idea rather than as a concrete, physical entity.
-
B.
isConceptualizedAs
Indicates that one entity is mentally represented, interpreted, or understood in terms of another entity.
-
C.
hasConceptualStructure
Indicates that one entity embodies, organizes, or is characterized by a particular conceptual structure defined by another entity.
-
D.
conceptualizedFor
Indicates that one entity has been conceived, designed, or mentally framed specifically for use, application, or relevance to another entity.
-
E.
isConceptuallyReflective
Indicates that one entity mirrors, represents, or echoes the ideas, structure, or meaning of another at a conceptual level.
- 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_69e0c45d95a081908e7962ad215da746 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee884bfa548190a39e5992ed6bb8a8 |
completed | April 26, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69e6320043bc81909417c41a718652ba |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:26 p.m.