Triple
T19674167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Israelite army |
E472409
|
entity |
| Predicate | isStationedOn |
P88394
|
FINISHED |
| Object | one hill opposite the Philistines |
—
|
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: one hill opposite the Philistines | Statement: [Israelite army, isStationedOn, one hill opposite the Philistines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isStationedOn Context triple: [Israelite army, isStationedOn, one hill opposite the Philistines]
-
A.
stationedOn
chosen
Indicates that an entity is assigned to remain at a specific location, platform, or vehicle for duty or operational purposes.
-
B.
hasStationAt
Indicates that an entity maintains or operates a station located at a specified place.
-
C.
isSurfaceStation
Indicates that the station is located at or on the surface (e.g., ground level) rather than being underground, elevated, or otherwise non-surface.
-
D.
hasStationNear
Indicates that one entity has a station located in close proximity to another entity.
-
E.
ownedStation
Indicates that one entity possesses ownership or control over a particular station.
- 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_69d8e514f2e08190ba70a4449519d218 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6416e19d881909248c4f778f7147a |
completed | April 20, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_69e514eb37b8819091502cc954f70eba |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:45 p.m.