Triple
T15838133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William of Tyre |
E384033
|
entity |
| Predicate | see |
P1205
|
FINISHED |
| Object | Tyre |
E30369
|
NE 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: Tyre | Statement: [William of Tyre, see, Tyre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tyre Context triple: [William of Tyre, see, Tyre]
-
A.
Tyre
chosen
Tyre is an ancient Phoenician port city, in present-day Lebanon, renowned as a major maritime, commercial, and cultural center of the Mediterranean world.
-
B.
Tarsos
Tarsos is the ancient name of the historic city of Tarsus in Cilicia, a significant cultural and commercial center in the eastern Mediterranean world.
-
C.
Suret
Suret is a modern Eastern Neo-Aramaic language spoken primarily by Assyrian communities in parts of Iraq, Syria, Iran, and the global diaspora.
-
D.
Tournor
Tournor is a surname variant of "Turnor," typically of English origin.
-
E.
Trun
Trun is a commune in northwestern France that became historically significant as a focal point in the closing encirclement of German forces during the Battle of the Falaise Pocket in World War II.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d86da34c888190976e06c4019d415a |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e142e3d48c8190ad0d0af89d062101 |
completed | April 16, 2026, 8:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa13a83448190adcad8bb84622e55 |
completed | May 9, 2026, 9:03 p.m. |
Created at: April 10, 2026, 4:49 a.m.