Triple
T31651894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matthew Maule |
E807750
|
entity |
| Predicate | propertyLost |
P166417
|
FINISHED |
| Object | land later used for the House of the Seven Gables |
—
|
LITERAL 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: land later used for the House of the Seven Gables | Statement: [Matthew Maule, propertyLost, land later used for the House of the Seven Gables]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: propertyLost Context triple: [Matthew Maule, propertyLost, land later used for the House of the Seven Gables]
-
A.
lostOwnershipOf
chosen
Indicates that an entity no longer possesses or holds ownership of another entity it previously owned.
-
B.
changesProperty
Indicates that one entity causes a change in a specific property or attribute of another entity.
-
C.
notableItemLost
Indicates that an entity has lost a particular item that is considered notable or significant.
-
D.
canBeLostBy
Indicates that something is capable of being lost or forfeited by a particular entity.
-
E.
lostSupportOf
Indicates that one entity no longer has the backing, approval, or endorsement of another entity that previously supported it.
- 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_69f348daf95c81908b4c985b7ddcd0b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6d16f5cb881908eed141afaaa0b51 |
completed | May 3, 2026, 4:39 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe45554819089cbbd538d992132 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 30, 2026, 10:53 p.m.