Triple
T29251106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phrygian alphabet |
E741568
|
entity |
| Predicate | primaryEvidenceSites |
P91331
|
FINISHED |
| Object | Gordion |
—
|
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: Gordion | Statement: [Phrygian alphabet, primaryEvidenceSites, Gordion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryEvidenceSites Context triple: [Phrygian alphabet, primaryEvidenceSites, Gordion]
-
A.
primarySites
Indicates the main or originating locations associated with an entity, often distinguishing them from secondary or related sites.
-
B.
earliestEvidenceSite
chosen
Indicates that the related site is the location where the earliest known evidence of the subject was found.
-
C.
primarySources
Indicates that one entity serves as an original, authoritative source of information or evidence for another entity.
-
D.
providesEvidenceFor
Indicates that one entity serves as support, justification, or proof for the validity or truth of another entity.
-
E.
primaryRecordingSite
Indicates the main anatomical or spatial location where a recording or measurement was originally captured.
- 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_69f0911eba2c8190b07cd2fdf91422c9 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_6a00d08e8fac8190b59359134e6e1c03 |
completed | May 10, 2026, 6:38 p.m. |
| PD | Predicate disambiguation | batch_6a00d0127c088190a6f5b360450af113 |
completed | May 10, 2026, 6:36 p.m. |
Created at: April 28, 2026, 12:34 p.m.