Triple
T28518906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Calla Bryn Sturgis |
E721701
|
entity |
| Predicate | defendedByGroup |
P15009
|
FINISHED |
| Object |
Roland's ka-tet
Roland's ka-tet is the tightly bound fellowship of gunslingers and allies who accompany Roland Deschain on his quest for the Dark Tower in Stephen King’s fantasy series.
|
E1822185
|
NE FINISHED |
How this triple was built (3 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: Roland's ka-tet | Statement: [Calla Bryn Sturgis, defendedByGroup, Roland's ka-tet]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Roland's ka-tet Triple: [Calla Bryn Sturgis, defendedByGroup, Roland's ka-tet]
Generated description
Roland's ka-tet is the tightly bound fellowship of gunslingers and allies who accompany Roland Deschain on his quest for the Dark Tower in Stephen King’s fantasy series.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defendedByGroup Context triple: [Calla Bryn Sturgis, defendedByGroup, Roland's ka-tet]
-
A.
titleDefendedBy
Indicates that a specific title or championship is actively defended or held against challengers by a particular entity.
-
B.
defendedAs
Indicates that one entity is presented, argued, or justified as being equivalent to or serving the role of another entity in a defensive or protective context.
-
C.
defenceHandledBy
chosen
Indicates that responsibility for managing or conducting a defence is assigned to or carried out by a particular agent or entity.
-
D.
defendedOn
Indicates that one entity protected, supported, or argued in favor of another entity during a specific time or event.
-
E.
opposedByGroup
Indicates that an action, proposal, or entity is met with opposition or resistance from a particular group.
- F. None of above.
Provenance (6 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_69f01a5cbcc4819083fb4e723378713e |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a1cac56d2a48190ba4141896d36761c |
completed | May 31, 2026, 9:47 p.m. |
| NEDg | Description generation | batch_6a1cacfd783481909760a61d90ab904b |
completed | May 31, 2026, 9:49 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a1cadd09b908190afc24c7665a804c4 |
completed | May 31, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 28, 2026, 3:19 a.m.