Triple
T37214151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earl of Ellenborough |
E922688
|
entity |
| Predicate | hasFirstHolderDeathYear |
P16526
|
FINISHED |
| Object | 1871 |
—
|
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: 1871 | Statement: [Earl of Ellenborough, hasFirstHolderDeathYear, 1871]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFirstHolderDeathYear Context triple: [Earl of Ellenborough, hasFirstHolderDeathYear, 1871]
-
A.
secondHolderDeathYear
Indicates the calendar year in which the second holder of something (such as a title, position, or asset) died.
-
B.
firstHolderDeathDate
Indicates the date on which the initial or original holder of something (such as a title, account, or asset) died.
-
C.
lastHolderDiedIn
Indicates that the most recent holder or possessor of something died in the specified place or during the specified event or time period.
-
D.
yearOfDeath
chosen
Indicates the specific year in which an entity (typically a person or organism) died.
-
E.
namedAfterDateOfDeath
Indicates that something is named after an entity specifically using the date on which that entity died.
- 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_69f76ea6f5288190b8d9988f613811c0 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a004fd3caf48190b2ec063a7bf0756b |
completed | May 10, 2026, 9:28 a.m. |
| PD | Predicate disambiguation | batch_6a004f7672dc8190aca91d1ed855bf9a |
completed | May 10, 2026, 9:27 a.m. |
Created at: May 3, 2026, 4:15 p.m.