Triple
T37703416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sudley Ford road |
E939128
|
entity |
| Predicate | approachedBattlefield |
P117785
|
FINISHED |
| Object | Manassas battlefield |
—
|
NE NERFINISHED |
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: Manassas battlefield | Statement: [Sudley Ford road, approachedBattlefield, Manassas battlefield]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approachedBattlefield Context triple: [Sudley Ford road, approachedBattlefield, Manassas battlefield]
-
A.
entersBattle
Indicates that an entity initiates participation in a battle or combat situation.
-
B.
approachArea
chosen
Indicates that an entity moves toward or comes closer to a specified area or region.
-
C.
combatArea
Indicates a designated location or zone where combat or fighting activities take place or are authorized.
-
D.
battlegroundFor
Indicates that a location serves as the site or arena where a conflict, competition, or struggle between entities takes place.
-
E.
battlefieldOf
Indicates that a location is the site where a particular battle or military engagement took place.
- 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_69f76edb49dc8190b951dce9ce6ef789 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffc7b4c7f88190b6357a44e7f0940f |
completed | May 9, 2026, 11:48 p.m. |
| PD | Predicate disambiguation | batch_69ffc755f09c8190995ca00d97336988 |
completed | May 9, 2026, 11:46 p.m. |
Created at: May 3, 2026, 4:18 p.m.