Triple
T22460127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Farquhar |
E555206
|
entity |
| Predicate | officeStartForRole:ResidentOfSingapore |
P148279
|
FINISHED |
| Object | 1819 |
—
|
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: 1819 | Statement: [William Farquhar, officeStartForRole:ResidentOfSingapore, 1819]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeStartForRole:ResidentOfSingapore Context triple: [William Farquhar, officeStartForRole:ResidentOfSingapore, 1819]
-
A.
usedForResidentsOf
Indicates that something is intended to be used by, or serves the needs of, people who reside in a particular place or region.
-
B.
hostResidenceOf
Indicates that a location serves as the primary place of residence for a specified person or group.
-
C.
accessToPrimarySettlement
Indicates that an entity has the ability or right to reach, use, or benefit from a designated primary settlement.
-
D.
officeStartTime (Administrator of UNDP)
Indicates the date and time at which the person began serving as Administrator of UNDP.
-
E.
residesInWork
Indicates that a person or entity lives or is based within the location, setting, or environment defined by a particular work (such as a book, film, or other creative piece).
- F. None of above. chosen
Provenance (4 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b7eb5688190bd5e41d4d8189668 |
completed | April 29, 2026, 1:14 a.m. |
| PD | Predicate disambiguation | batch_69e898ad961c819098fd1e46129bddcc |
completed | April 22, 2026, 9:45 a.m. |
| PDg | Predicate description generation | batch_69e8aa39e3388190b659d59948ebf3e6 |
completed | April 22, 2026, 11 a.m. |
Created at: April 16, 2026, 8:48 p.m.