Triple
T3099191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laban |
E64673
|
entity |
| Predicate | residesIn |
P75
|
FINISHED |
| Object | Haran |
E52250
|
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: Haran | Statement: [Laban, residesIn, Haran]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Haran Context triple: [Laban, residesIn, Haran]
-
A.
Haran
chosen
Haran is an ancient city in northern Mesopotamia known from the Hebrew Bible as a key dwelling place of the patriarch Abraham before his journey to Canaan.
-
B.
Bettiah
Bettiah is a prominent town and administrative center in the West Champaran district of the Indian state of Bihar, known historically for its role in the indigo movement and regional trade.
-
C.
Nahor
Nahor is a biblical patriarch mentioned in the Book of Genesis, known as a brother of Abraham and an ancestor within the lineage of the Israelites.
-
D.
Erechim
Erechim is a city in southern Brazil known for its strong German-Brazilian cultural heritage and influence.
-
E.
Libnah
Libnah was a woman of the royal family of Judah, known primarily as the wife of King Josiah and the mother of King Zedekiah.
- 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_69ad857dc98481909e585dc3372e3ed5 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada269a9188190aada5b3799d4dfd7 |
completed | March 8, 2026, 4:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2037cc5fc819084a441ebb045142b |
completed | March 12, 2026, 12:06 a.m. |
Created at: March 8, 2026, 3:03 p.m.