Triple
T35481827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dark Sister |
E1025489
|
entity |
| Predicate | firstKnownOwner |
P153898
|
FINISHED |
| Object | Visenya Targaryen |
E1025487
|
NE 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: Visenya Targaryen | Statement: [Dark Sister, firstKnownOwner, Visenya Targaryen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstKnownOwner Context triple: [Dark Sister, firstKnownOwner, Visenya Targaryen]
-
A.
initialOwner
Indicates the entity that originally possessed, controlled, or owned another entity before any subsequent transfers or changes in ownership.
-
B.
first_holder
chosen
Indicates that the subject is the earliest or original holder or possessor of the specified object, title, or right.
-
C.
firstHoldersBelongedTo
Indicates that the initial holders or owners of something were members of, or affiliated with, a particular group, organization, or category.
-
D.
firstAcquiredBy
Indicates the entity that initially obtained, purchased, or took ownership of something for the first time.
-
E.
firstModernHolder
Indicates that the subject is the earliest or original modern entity to hold or possess the specified object, title, or role.
- F. None of above.
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_69f76dfadba0819083456aadcd6864ea |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a38726c71bc81909f77eae2d4ffa442 |
completed | June 21, 2026, 11:23 p.m. |
| PD | Predicate disambiguation | batch_6a037a0324d08190ac5b610cc0f6a38c |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:04 p.m.