Triple
T31224949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shrike |
E796111
|
entity |
| Predicate | USDesignation |
P97629
|
FINISHED |
| Object | AGM-45 |
—
|
NE NERFINISHED |
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: AGM-45 | Statement: [Shrike, USDesignation, AGM-45]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: USDesignation Context triple: [Shrike, USDesignation, AGM-45]
-
A.
americanDesignation
chosen
Indicates that one entity is the official American name, title, or designation for another entity.
-
B.
hasUSFDADesignation
Indicates that an entity has been granted a specific formal designation or status by the U.S. Food and Drug Administration (FDA).
-
C.
NASADesignation
Indicates that an entity has been assigned an official identification or catalog number by NASA.
-
D.
stateDesignation
Indicates that an entity has been formally assigned or recognized with a particular status, title, or classification by an official authority or governing body.
-
E.
internationalDesignation
Indicates that an entity has been assigned a formal status, code, or recognition by an international body or under an internationally agreed system.
- 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_69f224da98f88190ab32f690cce5d303 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69c5030b88190bac4667e104238af |
completed | May 3, 2026, 12:52 a.m. |
| PD | Predicate disambiguation | batch_69f696673214819094350e1d2648ef34 |
completed | May 3, 2026, 12:27 a.m. |
Created at: April 29, 2026, 9:10 p.m.