Triple
T38241146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poverty in Flea Bottom |
E1013762
|
entity |
| Predicate | witnessedByCharacter |
P106748
|
FINISHED |
| Object | Arya Stark |
—
|
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: Arya Stark | Statement: [Poverty in Flea Bottom, witnessedByCharacter, Arya Stark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: witnessedByCharacter Context triple: [Poverty in Flea Bottom, witnessedByCharacter, Arya Stark]
-
A.
experiencedByCharacter
chosen
Indicates that a particular event, situation, or emotion is undergone or lived through by a specific character.
-
B.
exposedByCharacter
Indicates that one character reveals, uncovers, or discloses something about another character or their actions.
-
C.
givenByCharacter
Indicates that something (such as an item, information, or assistance) is provided or handed over by a particular character.
-
D.
attendedByFictionalCharacter
Indicates that a fictional character is present at, participates in, or is an attendee of a particular event or gathering.
-
E.
ledByCharacter
Indicates that an event, group, or activity is directed or guided by a specific character.
- 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_69f76dd72a248190a5fe18db2bd1eb15 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fcc3321ef081908023590ba70ba0cf |
completed | May 7, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69fcb0fdc6e08190b05e894c59481a0d |
completed | May 7, 2026, 3:34 p.m. |
Created at: May 3, 2026, 4:30 p.m.