Triple
T23647424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King of Greece |
E584075
|
entity |
| Predicate | lastHolderStart |
P153025
|
FINISHED |
| Object | 1964 |
—
|
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: 1964 | Statement: [King of Greece, lastHolderStart, 1964]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastHolderStart Context triple: [King of Greece, lastHolderStart, 1964]
-
A.
currentHolderStart
Indicates the point in time when an entity’s current holder or possessor first began holding it.
-
B.
lastHolder
Indicates that the subject is the most recent entity to have possessed, owned, or held the object.
-
C.
lastHolderAsCount
Indicates that the referenced entity was the most recent holder of something, with the relationship expressed in terms of a count or number of times it held that thing.
-
D.
firstHolderEnd
Indicates that the specified entity is the one who initially held something and that this holding relationship has come to an end.
-
E.
lastHolderRank
Indicates the rank or position held by the most recent entity that possessed or held a given item, title, or role.
- 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_69e248fefafc81909656921192f30e80 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b28643348190add3666638951680 |
completed | April 29, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f118d7903c8190bb590a71771e93af |
completed | April 28, 2026, 8:30 p.m. |
| PDg | Predicate description generation | batch_69f1233300bc8190ac1639bdca1d7d99 |
completed | April 28, 2026, 9:14 p.m. |
Created at: April 17, 2026, 6:48 p.m.