Triple
T14939991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Williamsburg |
E372497
|
entity |
| Predicate | involvesPursuitOf |
P57748
|
FINISHED |
| Object | retreating Confederate forces from Yorktown defenses |
—
|
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: retreating Confederate forces from Yorktown defenses | Statement: [Battle of Williamsburg, involvesPursuitOf, retreating Confederate forces from Yorktown defenses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvesPursuitOf Context triple: [Battle of Williamsburg, involvesPursuitOf, retreating Confederate forces from Yorktown defenses]
-
A.
involves
Indicates that an entity participates in, is a part of, or is implicated within a particular event, process, or relationship.
-
B.
soughtTo
Indicates that one entity attempted or intended to obtain, achieve, or bring about another entity or outcome.
-
C.
pursuingCharacter
chosen
Indicates that one character is actively chasing, seeking, or attempting to catch or reach another character.
-
D.
isSoughtBy
Indicates that one entity is actively being searched for, pursued, or desired by another entity.
-
E.
oftenInvolvedWith
Indicates that one entity frequently participates in or is commonly associated with activities, events, or situations involving another entity.
- 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_69d85cc9da0c81908d583ca3f63a3908 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded64a2f24819099b21566756668a2 |
completed | April 15, 2026, 12:05 a.m. |
| PD | Predicate disambiguation | batch_69de9a588c2c8190b1245a1c406f447c |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:38 a.m.