Triple
T29187970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Captain Doza |
E739920
|
entity |
| Predicate | commandedLocation |
P61316
|
FINISHED |
| Object | Colossus control tower |
—
|
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: Colossus control tower | Statement: [Captain Doza, commandedLocation, Colossus control tower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commandedLocation Context triple: [Captain Doza, commandedLocation, Colossus control tower]
-
A.
locationOfCommand
chosen
Indicates that a specified place or facility serves as the site from which a particular command or authority is exercised.
-
B.
commandedTo
Indicates that one entity has issued an order or directive for another entity to perform a specific action or fulfill a particular duty.
-
C.
commanderPosition
Indicates that one entity holds the role or position of commander in relation to another entity.
-
D.
commandedIn
Indicates that one entity held a position of command or leadership within a specified context, such as a battle, operation, or organization.
-
E.
commandedFor
Indicates that one entity issued an order or directive on behalf of, or in service of, another entity or purpose.
- 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_69f07cb8033c8190b8807e219a14333d |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f6f8565134819096aac0175f924a9f |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f65fd1d08190b88e5e68ba268500 |
completed | May 3, 2026, 7:16 a.m. |
Created at: April 28, 2026, noon