Triple
T29076310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serdika |
E735948
|
entity |
| Predicate | hasRemainsUnder |
P16216
|
FINISHED |
| Object | Largo complex in Sofia |
—
|
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: Largo complex in Sofia | Statement: [Serdika, hasRemainsUnder, Largo complex in Sofia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRemainsUnder Context triple: [Serdika, hasRemainsUnder, Largo complex in Sofia]
-
A.
hasRemainsOf
chosen
Indicates that one entity physically contains, preserves, or is associated with the leftover physical traces or remnants of another entity.
-
B.
hasRemainderTo
Indicates that one quantity leaves a specified remainder when divided by another quantity.
-
C.
remainedIn
Indicates that an entity stayed within or continued to be located in a particular place or state for a period of time.
-
D.
holdsUnder
Indicates that one entity maintains possession, control, or validity of another entity subject to certain conditions, constraints, or a specific context.
-
E.
estimatedNumberOfRemains
Indicates the approximate count of human or other remains associated with an entity, based on estimation rather than an exact measurement.
- 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_69f077e9b0a48190bb79548279cb7f64 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69ffb1f0b03c81909ddb81f07ce74e88 |
completed | May 9, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69ffb1662b2481908582e0612744f4c5 |
completed | May 9, 2026, 10:12 p.m. |
Created at: April 28, 2026, 10:23 a.m.