Triple
T37303549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Talos I |
E926018
|
entity |
| Predicate | laterOwnedByInFiction |
P90818
|
FINISHED |
| Object | TranStar Corporation |
—
|
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: TranStar Corporation | Statement: [Talos I, laterOwnedByInFiction, TranStar Corporation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterOwnedByInFiction Context triple: [Talos I, laterOwnedByInFiction, TranStar Corporation]
-
A.
formerOwnerInFiction
chosen
Indicates that one entity is depicted in a fictional context as having previously owned another entity.
-
B.
ownedByFictionalCharacter
Indicates that something is possessed or owned by a fictional (not real-world) character.
-
C.
laterInheritedByFictionalCharacter
Indicates that something originally associated with one entity is subsequently inherited or taken over by a fictional character.
-
D.
savedByInFiction
Indicates that, within a fictional narrative, one entity is rescued or saved by another entity.
-
E.
laterSettingOfFiction
Indicates that one fictional work is set chronologically later than another within a shared narrative or story world.
- 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_69f76eb1bc508190924e9fa5d8acdeb3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a00dc330b148190aaae2ac6a5327960 |
completed | May 10, 2026, 7:27 p.m. |
| PD | Predicate disambiguation | batch_6a00d9d2904881909dafbfe7b9e5ad81 |
completed | May 10, 2026, 7:17 p.m. |
Created at: May 3, 2026, 4:16 p.m.