Triple
T34805132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dover Patrol memorial |
E1003331
|
entity |
| Predicate | hasTwinMemorial |
P501
|
FINISHED |
| Object | Dover Patrol Monument, Dover |
E1003331
|
NE 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: Dover Patrol Monument, Dover | Statement: [Dover Patrol memorial, hasTwinMemorial, Dover Patrol Monument, Dover]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTwinMemorial Context triple: [Dover Patrol memorial, hasTwinMemorial, Dover Patrol Monument, Dover]
-
A.
hasSisterMemorial
Indicates that one entity has a memorial dedicated to or commemorating its sister.
-
B.
hasTwin
Indicates that one entity is a twin of another, sharing the same birth event or time with a sibling.
-
C.
hasTwinStatus
Indicates that an entity has a twin relationship or classification, such as being one of a pair of twins or having an associated twin counterpart.
-
D.
hasAdjacentMemorial
Indicates that one memorial is located directly next to or in close proximity to another memorial.
-
E.
hasMemorial
chosen
Indicates that a memorial exists in honor of, or dedicated to, a particular entity.
- F. None of above.
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_69f76db600b88190989abdf08fce3b27 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f77a8cf978819086a26dbbbd31d9a2 |
completed | May 3, 2026, 4:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a376fadb1b081909b7d30bfd3b7ca43 |
completed | June 21, 2026, 4:59 a.m. |
| PD | Predicate disambiguation | batch_69f7795b1abc8190823664d1caa94649 |
completed | May 3, 2026, 4:35 p.m. |
Created at: May 3, 2026, 3:59 p.m.