Triple
T34693382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyanna Stark |
E890958
|
entity |
| Predicate | lastRequestTo |
P179629
|
FINISHED |
| Object | Eddard 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: Eddard Stark | Statement: [Lyanna Stark, lastRequestTo, Eddard Stark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastRequestTo Context triple: [Lyanna Stark, lastRequestTo, Eddard Stark]
-
A.
lastRequest
Indicates that an entity is the most recent one to have made a particular request or initiated an interaction.
-
B.
lastUsedIn
Indicates that something was most recently utilized, applied, or referenced within a particular context, location, or instance.
-
C.
lastUsedFor
Indicates that one entity was the most recent purpose, function, or application for which another entity was used.
-
D.
lastSeen
Indicates the most recent time or occasion on which one entity observed, encountered, or had contact with another entity.
-
E.
lastSeenOn
Indicates the most recent time or date at which the subject entity was observed, detected, or recorded.
- 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_69f349db7ab8819086808e833f472871 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f723549ac8819088816d0c96e28251 |
completed | May 3, 2026, 10:28 a.m. |
| PD | Predicate disambiguation | batch_69f72157af108190880317a62e634bb0 |
completed | May 3, 2026, 10:20 a.m. |
| PDg | Predicate description generation | batch_69f7221bc57c819085c1464a45e61b2f |
completed | May 3, 2026, 10:23 a.m. |
Created at: May 1, 2026, 2:05 a.m.