Triple
T17047485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Marshal, 2nd Earl of Pembroke |
E413606
|
entity |
| Predicate | territorialLordship |
P47636
|
FINISHED |
| Object | Longueville |
E909223
|
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: Longueville | Statement: [William Marshal, 2nd Earl of Pembroke, territorialLordship, Longueville]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Longueville Context triple: [William Marshal, 2nd Earl of Pembroke, territorialLordship, Longueville]
-
A.
Longueville
chosen
Longueville is a historical French territorial domain associated with the noble House of Orléans-Longueville.
-
B.
Longueville
Longueville is a harbourside residential suburb on Sydney’s Lower North Shore, known for its waterfront views and affluent, leafy streets.
-
C.
Saicourt
Saicourt is a small municipality in the French-speaking Jura bernois region of the canton of Bern in Switzerland.
-
D.
Turqueville
Turqueville is a small commune in the Manche department of northwestern France, situated in the Normandy region.
-
E.
Lagrenée
Lagrenée is a French surname most notably associated with the 18th-century painter Louis Lagrenée.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3da9f799c8190a683ae38cd990643 |
completed | April 18, 2026, 7:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01233fb8d88190a9a6ef6a2f19a499 |
completed | May 11, 2026, 12:30 a.m. |
Created at: April 10, 2026, 5:34 a.m.