Triple
T26588451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John de Vaux |
E667276
|
entity |
| Predicate | heldBarony |
P18060
|
FINISHED |
| Object |
barony of Dirleton
The barony of Dirleton was a medieval Scottish feudal lordship centered on Dirleton in East Lothian, historically associated with Dirleton Castle and the noble families who controlled this strategic coastal estate.
|
E1732027
|
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: barony of Dirleton | Statement: [John de Vaux, heldBarony, barony of Dirleton]
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: barony of Dirleton Triple: [John de Vaux, heldBarony, barony of Dirleton]
Generated description
The barony of Dirleton was a medieval Scottish feudal lordship centered on Dirleton in East Lothian, historically associated with Dirleton Castle and the noble families who controlled this strategic coastal estate.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldBarony Context triple: [John de Vaux, heldBarony, barony of Dirleton]
-
A.
companionBarony
Indicates a relationship where one barony is designated as an accompanying or associated barony to another, typically linked or paired in status or function.
-
B.
hasNotableBarony
chosen
Indicates that an entity possesses or is associated with a barony that is considered notable or significant in some context.
-
C.
heldFief
Indicates that one entity possessed or controlled a fief (a feudal estate or tenure) from another entity.
-
D.
historicBarony
Indicates that an entity has the status or role of a historic barony, i.e., it was once recognized as a baronial territorial or feudal jurisdiction.
-
E.
hasNumberOfCompanionBaronies
Indicates the specific count of companion baronies associated with a given entity.
- 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_69ee9cfb7e548190b60a9031182f5a7e |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f61f12b0f08190bc4a16907941864c |
completed | May 2, 2026, 3:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a11c838cb388190a6be7088e3155c68 |
completed | May 23, 2026, 3:31 p.m. |
| NEDg | Description generation | batch_6a11c945273c8190ac0bc6fe508a6d9a |
completed | May 23, 2026, 3:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a11ca6f162c8190a8c7fbc1e188ea90 |
completed | May 23, 2026, 3:40 p.m. |
| PD | Predicate disambiguation | batch_69f61b3a8ae0819090189fbd8eb19f2f |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 2:06 a.m.