Triple
T34641068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord of Winterfell |
E889557
|
entity |
| Predicate | associatedWithWords |
P8272
|
FINISHED |
| Object | Winter Is Coming |
E340464
|
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: Winter Is Coming | Statement: [Lord of Winterfell, associatedWithWords, Winter Is Coming]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithWords Context triple: [Lord of Winterfell, associatedWithWords, Winter Is Coming]
-
A.
associatedWithVerb
Indicates that one entity is connected or linked to another through some verb-based relationship or action.
-
B.
associatedWithText
chosen
Indicates that an entity has a contextual or semantic connection to a specific piece of text.
-
C.
associatedKeyword
Indicates that one entity is linked to or characterized by a particular keyword used for identification, categorization, or retrieval.
-
D.
associatedWithSee
Indicates a relationship where one entity is contextually or functionally linked to another through the act or concept of seeing or visual observation.
-
E.
associatedWithEpithet
Indicates that an entity is linked to or described by a particular epithet or descriptive label.
- 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_69f349d724848190b63ad3407e0006d9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3748f014e48190b7891f51615b7586 |
completed | June 21, 2026, 2:14 a.m. |
| PD | Predicate disambiguation | batch_6a0379fd7aac8190873077e63873aa72 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 2:04 a.m.