Triple
T32526165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Project Blue |
E831319
|
entity |
| Predicate | createdByCharacterGroup |
P198112
|
FINISHED |
| Object | U.S. government scientists (fictional) |
—
|
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: U.S. government scientists (fictional) | Statement: [Project Blue, createdByCharacterGroup, U.S. government scientists (fictional)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdByCharacterGroup Context triple: [Project Blue, createdByCharacterGroup, U.S. government scientists (fictional)]
-
A.
createdByCharacterRole
Indicates that something (such as a work, item, or event) was brought into existence or produced by an entity acting in a specific character role.
-
B.
creatorOfGroup
Indicates that one entity is the originator or founder responsible for creating a particular group.
-
C.
associatedWithCharacterGroup
Indicates that an entity has a connection or affiliation with a particular group of characters.
-
D.
createdByCharacterInUniverse
Indicates that something (such as a work, object, or concept) was created by a specific character within a particular fictional universe.
-
E.
titleCharacterGroup
Indicates that a group of characters is associated with or featured in the title of a work.
- F. None of above. chosen
Provenance (4 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_69f34923e1548190be0524205d8cdf8f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fecb4d02f881909a9ee97ce98000d5 |
completed | May 9, 2026, 5:51 a.m. |
| PD | Predicate disambiguation | batch_69fec9846c1c8190b317f0711f0755db |
completed | May 9, 2026, 5:43 a.m. |
| PDg | Predicate description generation | batch_69fecb4be24481908bda6197d7fc32f4 |
completed | May 9, 2026, 5:51 a.m. |
Created at: May 1, 2026, 1:01 a.m.