Triple
T33923394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | fortress at Kumma |
E869678
|
entity |
| Predicate | oppositeFortress |
P192590
|
FINISHED |
| Object | fortress at Semna |
—
|
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: fortress at Semna | Statement: [fortress at Kumma, oppositeFortress, fortress at Semna]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oppositeFortress Context triple: [fortress at Kumma, oppositeFortress, fortress at Semna]
-
A.
opposedFortification
Indicates that one entity actively resisted, challenged, or worked against the strengthening or fortifying of another entity or location.
-
B.
opposedSiegeBy
Indicates that one party actively resisted, countered, or worked against another party’s siege.
-
C.
fortressDefended
Indicates that a fortress is actively protected against threats or attacks by some defending force.
-
D.
fortressOriginallyBuiltBy
Indicates that a particular fortress was initially constructed by a specified builder or group.
-
E.
opposingForce
Indicates a relationship where one entity actively resists, counters, or works against the actions, goals, or influence of another entity.
- 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_69f349992c508190aa4afa24a086cc8c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd19f791f48190bbb6f6047f9ddc59 |
completed | May 7, 2026, 11:02 p.m. |
| PD | Predicate disambiguation | batch_69fd0df365948190bc9bfc7ffd46acd8 |
completed | May 7, 2026, 10:10 p.m. |
| PDg | Predicate description generation | batch_69fd19f6a7888190aa7eee2b87687c53 |
completed | May 7, 2026, 11:02 p.m. |
Created at: May 1, 2026, 1:49 a.m.