Triple
T1579361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chris Patten |
E33725
|
entity |
| Predicate | wasLastHolderOfOffice |
P13875
|
FINISHED |
| Object | Governor of Hong Kong |
—
|
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: Governor of Hong Kong | Statement: [Chris Patten, wasLastHolderOfOffice, Governor of Hong Kong]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasLastHolderOfOffice Context triple: [Chris Patten, wasLastHolderOfOffice, Governor of Hong Kong]
-
A.
lastIncumbent
chosen
Indicates that the subject is the most recent person or entity to have held a particular position, office, or role before the current one.
-
B.
lastPresident
Indicates that one entity is the most recent individual to have held the office of president of the other entity.
-
C.
hasPresident
Indicates that an entity holds the position or role of president for another entity.
-
D.
previousPresident
Indicates that one person held the office of president immediately before another person.
-
E.
presidentSince
Indicates that one entity has held the office of president of another entity starting from a specified point in time.
- 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_69a885f27a4c8190a4622252cdf54c00 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abacfb1144819080c5687175aba1e1 |
completed | March 7, 2026, 4:43 a.m. |
| PD | Predicate disambiguation | batch_69aa61b0f5bc8190b1dc272990a59c13 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:27 p.m.