Triple
T33217181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Longbeards |
E850318
|
entity |
| Predicate | laterStronghold |
P1090
|
FINISHED |
| Object | Erebor |
—
|
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: Erebor | Statement: [Longbeards, laterStronghold, Erebor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterStronghold Context triple: [Longbeards, laterStronghold, Erebor]
-
A.
currentStronghold
Indicates that an entity currently serves as the primary base, fortress, or central stronghold for another entity.
-
B.
involvedStronghold
Indicates that an entity participates in or is significantly connected to a fortified place or stronghold within the context of an event or relationship.
-
C.
strongholdOf
Indicates that a location serves as a primary fortified base, center of power, or main stronghold for a particular entity.
-
D.
strongholdRecapturedBy
Indicates that control of a previously held stronghold has been regained by a specified entity after it was lost or captured.
-
E.
historicalStronghold
chosen
Indicates that a location has historically served as a fortified center of power, defense, or control for a group or authority.
- 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_69f3496083dc8190b229bb6932dc548b |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69ffc89596d08190b97bd60b45c7f9c0 |
completed | May 9, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69ffc81ba5dc8190ae94d44e2284948f |
completed | May 9, 2026, 11:49 p.m. |
Created at: May 1, 2026, 1:30 a.m.