Triple
T35984891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Echo Base defenders |
E1040681
|
entity |
| Predicate | followedOrdersFrom |
P132292
|
FINISHED |
| Object | Princess Leia Organa |
—
|
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: Princess Leia Organa | Statement: [Echo Base defenders, followedOrdersFrom, Princess Leia Organa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followedOrdersFrom Context triple: [Echo Base defenders, followedOrdersFrom, Princess Leia Organa]
-
A.
followsOrderFrom
chosen
Indicates that one entity complies with and acts according to the instructions or commands issued by another entity.
-
B.
followedIn
Indicates that one entity began following or subscribing to another entity, typically in a social or sequential context.
-
C.
followsBy
Indicates that one event, state, or entity occurs or comes immediately after another in a sequence or order.
-
D.
followsUnder
Indicates that one entity follows or proceeds after another while remaining within the scope, authority, or context defined by that other entity.
-
E.
followedCustom
Indicates that one entity chose to follow another entity according to a specific, non-standard or user-defined rule or configuration.
- 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_69f76e28293c8190ae3f4e2208b87117 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff234f32888190a1d800a3bda432eb |
completed | May 9, 2026, 12:06 p.m. |
| PD | Predicate disambiguation | batch_69ff228ae9a0819083f4b97c10b923f4 |
completed | May 9, 2026, 12:03 p.m. |
Created at: May 3, 2026, 4:07 p.m.