Triple
T52698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Raytheon Company |
E1034
|
entity |
| Predicate | keyTechnology |
P1485
|
FINISHED |
| Object | guided missile technology |
—
|
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: guided missile technology | Statement: [Raytheon Company, keyTechnology, guided missile technology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyTechnology Context triple: [Raytheon Company, keyTechnology, guided missile technology]
-
A.
keyTerm
Indicates that a term functions as a primary or central concept within a given context or information structure.
-
B.
technologyType
Indicates the specific kind or category of technology associated with an entity or relationship.
-
C.
technologyLevel
Indicates the degree of technological advancement or sophistication associated with an entity relative to others or to a defined scale.
-
D.
typicalKey
Indicates that the referenced key is the standard or most commonly used key associated with an entity or context.
-
E.
associatedWithTechnology
chosen
Indicates a relationship where an entity is connected to, involved with, or utilizes a particular technology.
- 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24c709c248190bcd442c8d508e48c |
completed | Feb. 28, 2026, 2:01 a.m. |
| PD | Predicate disambiguation | batch_69a24ac3c8dc819099849023bdaa35a9 |
completed | Feb. 28, 2026, 1:54 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.